Skip to content

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Rust

add grok 4.7 to every provider that serves it (#2505)

ktaa242fb2c00c
diff --git a/packages/ai/.changes/grok-4.7-support.md b/packages/ai/.changes/grok-4.7-support.md
new file mode 100644
index 0000000000..6fd7f85ff8
--- /dev/null
+++ b/packages/ai/.changes/grok-4.7-support.md
@@ -0,0 +1,3 @@
+- Added Grok 4.7 to the xAI, Grok subscription, OpenRouter, Vercel AI Gateway, and OpenCode Go model catalogs, with verified low through xhigh reasoning efforts on the subscription route.
+- Refreshed the generated model catalog from live provider catalogs, picking up upstream model additions, repricing, and retirements.
+- Pinned the shipped Kimi For Coding model rows after models.dev split the section into deployments that no longer match the provider's verified api.kimi.com endpoint.
diff --git a/packages/ai/scripts/generate-models.ts b/packages/ai/scripts/generate-models.ts
index c1e170d3cd..4105cef2fd 100644
--- a/packages/ai/scripts/generate-models.ts
+++ b/packages/ai/scripts/generate-models.ts
@@ -2052,6 +2052,72 @@ async function generateModels() {
});
}
+ // Pin the shipped Kimi For Coding rows. models.dev split the retired
+ // kimi-for-coding section into kimi-code-plan-global (api.kimi.ai) and
+ // kimi-code-plan-cn, both re-registered as OpenAI-compatible deployments
+ // that do not match this provider's verified Anthropic-messages surface on
+ // api.kimi.com/coding. Keep the existing rows until the provider is
+ // migrated to one of the new deployments with verified request shapes.
+ const kimiCodingModels: Model<"anthropic-messages">[] = [
+ {
+ id: "k3",
+ name: "Kimi K3",
+ api: "anthropic-messages",
+ provider: "kimi-coding",
+ baseUrl: "https://api.kimi.com/coding",
+ headers: { ...KIMI_STATIC_HEADERS },
+ reasoning: true,
+ input: ["text", "image"],
+ cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+ contextWindow: 1048576,
+ maxTokens: 131072,
+ },
+ {
+ id: "k3-256k",
+ name: "Kimi K3-256K",
+ api: "anthropic-messages",
+ provider: "kimi-coding",
+ baseUrl: "https://api.kimi.com/coding",
+ headers: { ...KIMI_STATIC_HEADERS },
+ reasoning: true,
+ input: ["text", "image"],
+ cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+ contextWindow: 262144,
+ maxTokens: 131072,
+ },
+ {
+ id: "kimi-for-coding",
+ name: "Kimi K2.7 Code",
+ api: "anthropic-messages",
+ provider: "kimi-coding",
+ baseUrl: "https://api.kimi.com/coding",
+ headers: { ...KIMI_STATIC_HEADERS },
+ reasoning: true,
+ input: ["text", "image"],
+ cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+ contextWindow: 262144,
+ maxTokens: 32768,
+ },
+ {
+ id: "kimi-for-coding-highspeed",
+ name: "Kimi For Coding HighSpeed",
+ api: "anthropic-messages",
+ provider: "kimi-coding",
+ baseUrl: "https://api.kimi.com/coding",
+ headers: { ...KIMI_STATIC_HEADERS },
+ reasoning: true,
+ input: ["text", "image"],
+ cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+ contextWindow: 262144,
+ maxTokens: 32768,
+ },
+ ];
+ for (const kimiModel of kimiCodingModels) {
+ if (!allModels.some((m) => m.provider === "kimi-coding" && m.id === kimiModel.id)) {
+ allModels.push(kimiModel);
+ }
+ }
+
// Add missing Mistral Medium 3.5 model until models.dev includes it
if (!allModels.some(m => m.provider === "mistral" && m.id === "mistral-medium-3.5")) {
allModels.push({
diff --git a/packages/ai/src/models.generated.ts b/packages/ai/src/models.generated.ts
index b5ff751ed7..ca8159ca08 100644
--- a/packages/ai/src/models.generated.ts
+++ b/packages/ai/src/models.generated.ts
@@ -16,11 +16,11 @@ export const MODELS = {
cost: {
input: 0.33,
output: 2.75,
- cacheRead: 0,
- cacheWrite: 0,
+ cacheRead: 0.0825,
+ cacheWrite: 0.33,
},
- contextWindow: 128000,
- maxTokens: 4096,
+ contextWindow: 1000000,
+ maxTokens: 65535,
} satisfies Model<"bedrock-converse-stream">,
"amazon.nova-lite-v1:0": {
id: "amazon.nova-lite-v1:0",
@@ -34,10 +34,10 @@ export const MODELS = {
input: 0.06,
output: 0.24,
cacheRead: 0.015,
- cacheWrite: 0,
+ cacheWrite: 0.06,
},
contextWindow: 300000,
- maxTokens: 8192,
+ maxTokens: 10000,
} satisfies Model<"bedrock-converse-stream">,
"amazon.nova-micro-v1:0": {
id: "amazon.nova-micro-v1:0",
@@ -51,10 +51,10 @@ export const MODELS = {
input: 0.035,
output: 0.14,
cacheRead: 0.00875,
- cacheWrite: 0,
+ cacheWrite: 0.035,
},
contextWindow: 128000,
- maxTokens: 8192,
+ maxTokens: 10000,
} satisfies Model<"bedrock-converse-stream">,
"amazon.nova-pro-v1:0": {
id: "amazon.nova-pro-v1:0",
@@ -68,10 +68,10 @@ export const MODELS = {
input: 0.8,
output: 3.2,
cacheRead: 0.2,
- cacheWrite: 0,
+ cacheWrite: 0.8,
},
contextWindow: 300000,
- maxTokens: 8192,
+ maxTokens: 10000,
} satisfies Model<"bedrock-converse-stream">,
"anthropic.claude-fable-5": {
id: "anthropic.claude-fable-5",
@@ -170,8 +170,8 @@ export const MODELS = {
thinkingLevelMap: {"max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 25,
+ input: 5.5,
+ output: 27.5,
cacheRead: 0.5,
cacheWrite: 6.25,
},
@@ -259,13 +259,13 @@ export const MODELS = {
thinkingLevelMap: {"max":"max"},
input: ["text", "image"],
cost: {
- input: 3,
- output: 15,
- cacheRead: 0.3,
- cacheWrite: 3.75,
+ input: 3.3,
+ output: 16.5,
+ cacheRead: 0.33,
+ cacheWrite: 4.125,
},
contextWindow: 1000000,
- maxTokens: 64000,
+ maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
"anthropic.claude-sonnet-5": {
id: "anthropic.claude-sonnet-5",
@@ -285,6 +285,74 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
+ "apac.amazon.nova-lite-v1:0": {
+ id: "apac.amazon.nova-lite-v1:0",
+ name: "Nova Lite (APAC)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: false,
+ input: ["text", "image"],
+ cost: {
+ input: 0.063,
+ output: 0.252,
+ cacheRead: 0.01575,
+ cacheWrite: 0.063,
+ },
+ contextWindow: 300000,
+ maxTokens: 10000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "apac.amazon.nova-micro-v1:0": {
+ id: "apac.amazon.nova-micro-v1:0",
+ name: "Nova Micro (APAC)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: false,
+ input: ["text"],
+ cost: {
+ input: 0.037,
+ output: 0.148,
+ cacheRead: 0.00925,
+ cacheWrite: 0.037,
+ },
+ contextWindow: 128000,
+ maxTokens: 10000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "apac.amazon.nova-pro-v1:0": {
+ id: "apac.amazon.nova-pro-v1:0",
+ name: "Nova Pro (APAC)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: false,
+ input: ["text", "image"],
+ cost: {
+ input: 0.84,
+ output: 3.36,
+ cacheRead: 0.21,
+ cacheWrite: 0.84,
+ },
+ contextWindow: 300000,
+ maxTokens: 10000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "apac.anthropic.claude-sonnet-4-20250514-v1:0": {
+ id: "apac.anthropic.claude-sonnet-4-20250514-v1:0",
+ name: "Claude Sonnet 4 (APAC)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 3,
+ output: 15,
+ cacheRead: 0.3,
+ cacheWrite: 3.75,
+ },
+ contextWindow: 200000,
+ maxTokens: 64000,
+ } satisfies Model<"bedrock-converse-stream">,
"au.anthropic.claude-haiku-4-5-20251001-v1:0": {
id: "au.anthropic.claude-haiku-4-5-20251001-v1:0",
name: "Claude Haiku 4.5 (AU)",
@@ -294,10 +362,10 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
- input: 1,
- output: 5,
- cacheRead: 0.1,
- cacheWrite: 1.25,
+ input: 1.1,
+ output: 5.5,
+ cacheRead: 0.11,
+ cacheWrite: 1.375,
},
contextWindow: 200000,
maxTokens: 64000,
@@ -312,14 +380,32 @@ export const MODELS = {
thinkingLevelMap: {"max":"max"},
input: ["text", "image"],
cost: {
- input: 16.5,
- output: 82.5,
+ input: 5.5,
+ output: 27.5,
cacheRead: 0.5,
cacheWrite: 6.25,
},
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
+ "au.anthropic.claude-opus-4-7": {
+ id: "au.anthropic.claude-opus-4-7",
+ name: "Claude Opus 4.7 (AU)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.ap-southeast-2.amazonaws.com",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 5.5,
+ output: 27.5,
+ cacheRead: 0.55,
+ cacheWrite: 6.875,
+ },
+ contextWindow: 1000000,
+ maxTokens: 128000,
+ } satisfies Model<"bedrock-converse-stream">,
"au.anthropic.claude-opus-4-8": {
id: "au.anthropic.claude-opus-4-8",
name: "Claude Opus 4.8 (AU)",
@@ -330,10 +416,10 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 25,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 5.5,
+ output: 27.5,
+ cacheRead: 0.55,
+ cacheWrite: 6.875,
},
contextWindow: 1000000,
maxTokens: 128000,
@@ -348,10 +434,10 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 25,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 5.5,
+ output: 27.5,
+ cacheRead: 0.55,
+ cacheWrite: 6.875,
},
contextWindow: 1000000,
maxTokens: 128000,
@@ -365,10 +451,10 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
- input: 3,
- output: 15,
- cacheRead: 0.3,
- cacheWrite: 3.75,
+ input: 3.3,
+ output: 16.5,
+ cacheRead: 0.33,
+ cacheWrite: 4.125,
},
contextWindow: 200000,
maxTokens: 64000,
@@ -401,30 +487,30 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 2,
- output: 10,
- cacheRead: 0.2,
- cacheWrite: 2.5,
+ input: 2.2,
+ output: 11,
+ cacheRead: 0.22,
+ cacheWrite: 2.75,
},
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
- "deepseek.r1-v1:0": {
- id: "deepseek.r1-v1:0",
- name: "DeepSeek-R1",
+ "ca.amazon.nova-lite-v1:0": {
+ id: "ca.amazon.nova-lite-v1:0",
+ name: "Nova Lite (CA)",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
- reasoning: true,
- input: ["text"],
+ reasoning: false,
+ input: ["text", "image"],
cost: {
- input: 1.35,
- output: 5.4,
- cacheRead: 0,
- cacheWrite: 0,
+ input: 0.064,
+ output: 0.256,
+ cacheRead: 0.016,
+ cacheWrite: 0.064,
},
- contextWindow: 128000,
- maxTokens: 32768,
+ contextWindow: 300000,
+ maxTokens: 10000,
} satisfies Model<"bedrock-converse-stream">,
"deepseek.v3-v1:0": {
id: "deepseek.v3-v1:0",
@@ -445,7 +531,7 @@ export const MODELS = {
} satisfies Model<"bedrock-converse-stream">,
"deepseek.v3.2": {
id: "deepseek.v3.2",
- name: "DeepSeek-V3.2",
+ name: "DeepSeek V3.2",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -460,6 +546,74 @@ export const MODELS = {
contextWindow: 163840,
maxTokens: 81920,
} satisfies Model<"bedrock-converse-stream">,
+ "eu.amazon.nova-2-lite-v1:0": {
+ id: "eu.amazon.nova-2-lite-v1:0",
+ name: "Nova 2 Lite (EU)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.374,
+ output: 3.157,
+ cacheRead: 0.0935,
+ cacheWrite: 0.374,
+ },
+ contextWindow: 1000000,
+ maxTokens: 65535,
+ } satisfies Model<"bedrock-converse-stream">,
+ "eu.amazon.nova-lite-v1:0": {
+ id: "eu.amazon.nova-lite-v1:0",
+ name: "Nova Lite (EU)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
+ reasoning: false,
+ input: ["text", "image"],
+ cost: {
+ input: 0.069,
+ output: 0.276,
+ cacheRead: 0.01725,
+ cacheWrite: 0.069,
+ },
+ contextWindow: 300000,
+ maxTokens: 10000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "eu.amazon.nova-micro-v1:0": {
+ id: "eu.amazon.nova-micro-v1:0",
+ name: "Nova Micro (EU)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
+ reasoning: false,
+ input: ["text"],
+ cost: {
+ input: 0.04,
+ output: 0.16,
+ cacheRead: 0.01,
+ cacheWrite: 0.04,
+ },
+ contextWindow: 128000,
+ maxTokens: 10000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "eu.amazon.nova-pro-v1:0": {
+ id: "eu.amazon.nova-pro-v1:0",
+ name: "Nova Pro (EU)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
+ reasoning: false,
+ input: ["text", "image"],
+ cost: {
+ input: 0.92,
+ output: 3.68,
+ cacheRead: 0.23,
+ cacheWrite: 0.92,
+ },
+ contextWindow: 300000,
+ maxTokens: 10000,
+ } satisfies Model<"bedrock-converse-stream">,
"eu.anthropic.claude-fable-5": {
id: "eu.anthropic.claude-fable-5",
name: "Claude Fable 5 (EU)",
@@ -584,6 +738,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
+ "eu.anthropic.claude-sonnet-4-20250514-v1:0": {
+ id: "eu.anthropic.claude-sonnet-4-20250514-v1:0",
+ name: "Claude Sonnet 4 (EU)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 3,
+ output: 15,
+ cacheRead: 0.3,
+ cacheWrite: 3.75,
+ },
+ contextWindow: 200000,
+ maxTokens: 64000,
+ } satisfies Model<"bedrock-converse-stream">,
"eu.anthropic.claude-sonnet-4-5-20250929-v1:0": {
id: "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
name: "Claude Sonnet 4.5 (EU)",
@@ -617,7 +788,7 @@ export const MODELS = {
cacheWrite: 4.125,
},
contextWindow: 1000000,
- maxTokens: 64000,
+ maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
"eu.anthropic.claude-sonnet-5": {
id: "eu.anthropic.claude-sonnet-5",
@@ -637,6 +808,40 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
+ "eu.mistral.pixtral-large-2502-v1:0": {
+ id: "eu.mistral.pixtral-large-2502-v1:0",
+ name: "Pixtral Large (25.02) (EU)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
+ reasoning: false,
+ input: ["text", "image"],
+ cost: {
+ input: 2,
+ output: 6,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 128000,
+ maxTokens: 8192,
+ } satisfies Model<"bedrock-converse-stream">,
+ "global.amazon.nova-2-lite-v1:0": {
+ id: "global.amazon.nova-2-lite-v1:0",
+ name: "Nova 2 Lite (Global)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.3,
+ output: 2.5,
+ cacheRead: 0.075,
+ cacheWrite: 0.3,
+ },
+ contextWindow: 1000000,
+ maxTokens: 65535,
+ } satisfies Model<"bedrock-converse-stream">,
"global.anthropic.claude-fable-5": {
id: "global.anthropic.claude-fable-5",
name: "Claude Fable 5 (Global)",
@@ -779,6 +984,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
+ "global.anthropic.claude-sonnet-4-20250514-v1:0": {
+ id: "global.anthropic.claude-sonnet-4-20250514-v1:0",
+ name: "Claude Sonnet 4 (Global)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 3,
+ output: 15,
+ cacheRead: 0.3,
+ cacheWrite: 3.75,
+ },
+ contextWindow: 200000,
+ maxTokens: 64000,
+ } satisfies Model<"bedrock-converse-stream">,
"global.anthropic.claude-sonnet-4-5-20250929-v1:0": {
id: "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
name: "Claude Sonnet 4.5 (Global)",
@@ -812,7 +1034,7 @@ export const MODELS = {
cacheWrite: 3.75,
},
contextWindow: 1000000,
- maxTokens: 64000,
+ maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
"global.anthropic.claude-sonnet-5": {
id: "global.anthropic.claude-sonnet-5",
@@ -886,30 +1108,82 @@ export const MODELS = {
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
- "google.gemma-3-27b-it": {
- id: "google.gemma-3-27b-it",
- name: "Google Gemma 3 27B Instruct",
+ "global.openai.gpt-6-astra": {
+ id: "global.openai.gpt-6-astra",
+ name: "GPT-6 Astra (Global)",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
- reasoning: false,
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 0.12,
- output: 0.2,
- cacheRead: 0,
- cacheWrite: 0,
+ input: 10,
+ output: 50,
+ cacheRead: 1,
+ cacheWrite: 12.5,
},
- contextWindow: 202752,
- maxTokens: 8192,
+ contextWindow: 1050000,
+ maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
- "google.gemma-3-4b-it": {
- id: "google.gemma-3-4b-it",
- name: "Gemma 3 4B IT",
+ "global.xai.grok-4.6": {
+ id: "global.xai.grok-4.6",
+ name: "Grok 4.6 (Global)",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
- reasoning: false,
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 2,
+ output: 6,
+ cacheRead: 0.5,
+ cacheWrite: 0,
+ },
+ contextWindow: 500000,
+ maxTokens: 500000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "google.gemma-4-26b-a4b": {
+ id: "google.gemma-4-26b-a4b",
+ name: "Gemma 4 26B A4B IT",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.13,
+ output: 0.4,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 32768,
+ } satisfies Model<"bedrock-converse-stream">,
+ "google.gemma-4-31b": {
+ id: "google.gemma-4-31b",
+ name: "Gemma 4 31B IT",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.14,
+ output: 0.4,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 32768,
+ } satisfies Model<"bedrock-converse-stream">,
+ "google.gemma-4-e2b": {
+ id: "google.gemma-4-e2b",
+ name: "Gemma 4 E2B IT",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
input: ["text", "image"],
cost: {
input: 0.04,
@@ -917,8 +1191,61 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 128000,
- maxTokens: 4096,
+ contextWindow: 131072,
+ maxTokens: 8192,
+ } satisfies Model<"bedrock-converse-stream">,
+ "in.openai.gpt-5.6-luna": {
+ id: "in.openai.gpt-5.6-luna",
+ name: "GPT-5.6 Luna (India)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 0.22,
+ output: 1.32,
+ cacheRead: 0.022,
+ cacheWrite: 0.275,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "in.openai.gpt-5.6-terra": {
+ id: "in.openai.gpt-5.6-terra",
+ name: "GPT-5.6 Terra (India)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 2.2,
+ output: 13.2,
+ cacheRead: 0.22,
+ cacheWrite: 2.75,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "jp.amazon.nova-2-lite-v1:0": {
+ id: "jp.amazon.nova-2-lite-v1:0",
+ name: "Nova 2 Lite (JP)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.ap-northeast-1.amazonaws.com",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.396,
+ output: 3.311,
+ cacheRead: 0.099,
+ cacheWrite: 0.396,
+ },
+ contextWindow: 1000000,
+ maxTokens: 65535,
} satisfies Model<"bedrock-converse-stream">,
"jp.anthropic.claude-haiku-4-5-20251001-v1:0": {
id: "jp.anthropic.claude-haiku-4-5-20251001-v1:0",
@@ -929,10 +1256,10 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
- input: 1,
- output: 5,
- cacheRead: 0.1,
- cacheWrite: 1.25,
+ input: 1.1,
+ output: 5.5,
+ cacheRead: 0.11,
+ cacheWrite: 1.375,
},
contextWindow: 200000,
maxTokens: 64000,
@@ -947,10 +1274,10 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 25,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 5.5,
+ output: 27.5,
+ cacheRead: 0.55,
+ cacheWrite: 6.875,
},
contextWindow: 1000000,
maxTokens: 128000,
@@ -965,10 +1292,10 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 25,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 5.5,
+ output: 27.5,
+ cacheRead: 0.55,
+ cacheWrite: 6.875,
},
contextWindow: 1000000,
maxTokens: 128000,
@@ -983,10 +1310,10 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 25,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 5.5,
+ output: 27.5,
+ cacheRead: 0.55,
+ cacheWrite: 6.875,
},
contextWindow: 1000000,
maxTokens: 128000,
@@ -1000,10 +1327,10 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
- input: 3,
- output: 15,
- cacheRead: 0.3,
- cacheWrite: 3.75,
+ input: 3.3,
+ output: 16.5,
+ cacheRead: 0.33,
+ cacheWrite: 4.125,
},
contextWindow: 200000,
maxTokens: 64000,
@@ -1018,13 +1345,13 @@ export const MODELS = {
thinkingLevelMap: {"max":"max"},
input: ["text", "image"],
cost: {
- input: 3,
- output: 15,
- cacheRead: 0.3,
- cacheWrite: 3.75,
+ input: 3.3,
+ output: 16.5,
+ cacheRead: 0.33,
+ cacheWrite: 4.125,
},
contextWindow: 1000000,
- maxTokens: 64000,
+ maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
"jp.anthropic.claude-sonnet-5": {
id: "jp.anthropic.claude-sonnet-5",
@@ -1036,10 +1363,10 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 2,
- output: 10,
- cacheRead: 0.2,
- cacheWrite: 2.5,
+ input: 2.2,
+ output: 11,
+ cacheRead: 0.22,
+ cacheWrite: 2.75,
},
contextWindow: 1000000,
maxTokens: 128000,
@@ -1110,7 +1437,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1000000,
- maxTokens: 16384,
+ maxTokens: 8192,
} satisfies Model<"bedrock-converse-stream">,
"meta.llama4-scout-17b-instruct-v1:0": {
id: "meta.llama4-scout-17b-instruct-v1:0",
@@ -1126,12 +1453,12 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 3500000,
- maxTokens: 16384,
+ contextWindow: 10000000,
+ maxTokens: 8192,
} satisfies Model<"bedrock-converse-stream">,
"minimax.minimax-m2": {
id: "minimax.minimax-m2",
- name: "MiniMax M2",
+ name: "MiniMax-M2",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1148,7 +1475,7 @@ export const MODELS = {
} satisfies Model<"bedrock-converse-stream">,
"minimax.minimax-m2.1": {
id: "minimax.minimax-m2.1",
- name: "MiniMax M2.1",
+ name: "MiniMax-M2.1",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1165,7 +1492,7 @@ export const MODELS = {
} satisfies Model<"bedrock-converse-stream">,
"minimax.minimax-m2.5": {
id: "minimax.minimax-m2.5",
- name: "MiniMax M2.5",
+ name: "MiniMax-M2.5",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1221,7 +1548,7 @@ export const MODELS = {
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
reasoning: false,
- input: ["text"],
+ input: ["text", "image"],
cost: {
input: 0.2,
output: 0.2,
@@ -1255,7 +1582,7 @@ export const MODELS = {
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
reasoning: false,
- input: ["text"],
+ input: ["text", "image"],
cost: {
input: 0.15,
output: 0.15,
@@ -1313,7 +1640,7 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 128000,
+ contextWindow: 32768,
maxTokens: 4096,
} satisfies Model<"bedrock-converse-stream">,
"mistral.voxtral-small-24b-2507": {
@@ -1325,12 +1652,12 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 0.15,
- output: 0.35,
+ input: 0.1,
+ output: 0.3,
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 32000,
+ contextWindow: 32768,
maxTokens: 8192,
} satisfies Model<"bedrock-converse-stream">,
"moonshot.kimi-k2-thinking": {
@@ -1365,7 +1692,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262143,
- maxTokens: 16000,
+ maxTokens: 16384,
} satisfies Model<"bedrock-converse-stream">,
"nvidia.nemotron-nano-12b-v2": {
id: "nvidia.nemotron-nano-12b-v2",
@@ -1382,7 +1709,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 128000,
- maxTokens: 4096,
+ maxTokens: 8192,
} satisfies Model<"bedrock-converse-stream">,
"nvidia.nemotron-nano-3-30b": {
id: "nvidia.nemotron-nano-3-30b",
@@ -1398,8 +1725,8 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 128000,
- maxTokens: 4096,
+ contextWindow: 262144,
+ maxTokens: 8192,
} satisfies Model<"bedrock-converse-stream">,
"nvidia.nemotron-nano-9b-v2": {
id: "nvidia.nemotron-nano-9b-v2",
@@ -1415,8 +1742,8 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 128000,
- maxTokens: 4096,
+ contextWindow: 131072,
+ maxTokens: 8192,
} satisfies Model<"bedrock-converse-stream">,
"nvidia.nemotron-super-3-120b": {
id: "nvidia.nemotron-super-3-120b",
@@ -1525,6 +1852,24 @@ export const MODELS = {
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
+ "openai.gpt-6-astra": {
+ id: "openai.gpt-6-astra",
+ name: "GPT-6 Astra",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"xhigh":"xhigh","max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 11,
+ output: 55,
+ cacheRead: 1.1,
+ cacheWrite: 13.75,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"bedrock-converse-stream">,
"openai.gpt-oss-120b": {
id: "openai.gpt-oss-120b",
name: "gpt-oss-120b",
@@ -1599,7 +1944,7 @@ export const MODELS = {
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
- reasoning: false,
+ reasoning: true,
input: ["text"],
cost: {
input: 0.15,
@@ -1616,7 +1961,7 @@ export const MODELS = {
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
- reasoning: false,
+ reasoning: true,
input: ["text"],
cost: {
input: 0.07,
@@ -1629,7 +1974,7 @@ export const MODELS = {
} satisfies Model<"bedrock-converse-stream">,
"qwen.qwen3-235b-a22b-2507-v1:0": {
id: "qwen.qwen3-235b-a22b-2507-v1:0",
- name: "Qwen3 235B A22B 2507",
+ name: "Qwen3 235B-A22B Instruct 2507",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1646,7 +1991,7 @@ export const MODELS = {
} satisfies Model<"bedrock-converse-stream">,
"qwen.qwen3-32b-v1:0": {
id: "qwen.qwen3-32b-v1:0",
- name: "Qwen3 32B (dense)",
+ name: "Qwen3 32B",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1658,12 +2003,12 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 16384,
+ contextWindow: 32768,
maxTokens: 16384,
} satisfies Model<"bedrock-converse-stream">,
"qwen.qwen3-coder-30b-a3b-v1:0": {
id: "qwen.qwen3-coder-30b-a3b-v1:0",
- name: "Qwen3 Coder 30B A3B Instruct",
+ name: "Qwen3-Coder 30B-A3B Instruct",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1680,14 +2025,14 @@ export const MODELS = {
} satisfies Model<"bedrock-converse-stream">,
"qwen.qwen3-coder-480b-a35b-v1:0": {
id: "qwen.qwen3-coder-480b-a35b-v1:0",
- name: "Qwen3 Coder 480B A35B Instruct",
+ name: "Qwen3-Coder 480B-A35B Instruct",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
reasoning: false,
input: ["text"],
cost: {
- input: 0.22,
+ input: 0.45,
output: 1.8,
cacheRead: 0,
cacheWrite: 0,
@@ -1701,82 +2046,201 @@ export const MODELS = {
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
- reasoning: true,
+ reasoning: false,
input: ["text"],
cost: {
- input: 0.22,
- output: 1.8,
+ input: 0.5,
+ output: 1.2,
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 131072,
+ contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"bedrock-converse-stream">,
"qwen.qwen3-next-80b-a3b": {
id: "qwen.qwen3-next-80b-a3b",
- name: "Qwen/Qwen3-Next-80B-A3B-Instruct",
+ name: "Qwen3-Next 80B-A3B Instruct",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
reasoning: false,
input: ["text"],
cost: {
- input: 0.14,
- output: 1.4,
+ input: 0.15,
+ output: 1.2,
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 262000,
+ contextWindow: 262144,
maxTokens: 262000,
} satisfies Model<"bedrock-converse-stream">,
"qwen.qwen3-vl-235b-a22b": {
id: "qwen.qwen3-vl-235b-a22b",
- name: "Qwen/Qwen3-VL-235B-A22B-Instruct",
+ name: "Qwen3 VL 235B A22B Instruct",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
reasoning: false,
input: ["text", "image"],
cost: {
- input: 0.3,
- output: 1.5,
+ input: 0.53,
+ output: 2.66,
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 262000,
+ contextWindow: 262144,
maxTokens: 262000,
} satisfies Model<"bedrock-converse-stream">,
- "us.anthropic.claude-fable-5": {
- id: "us.anthropic.claude-fable-5",
- name: "Claude Fable 5 (US)",
+ "us-gov.openai.gpt-oss-120b-1:0": {
+ id: "us-gov.openai.gpt-oss-120b-1:0",
+ name: "gpt-oss-120b (GovCloud)",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
reasoning: true,
- thinkingLevelMap: {"off":null,"xhigh":"xhigh","max":"max"},
- input: ["text", "image"],
+ input: ["text"],
cost: {
- input: 10,
- output: 50,
- cacheRead: 1,
- cacheWrite: 12.5,
+ input: 0.18,
+ output: 0.72,
+ cacheRead: 0,
+ cacheWrite: 0,
},
- contextWindow: 1000000,
- maxTokens: 128000,
+ contextWindow: 128000,
+ maxTokens: 16384,
} satisfies Model<"bedrock-converse-stream">,
- "us.anthropic.claude-fable-5-1": {
- id: "us.anthropic.claude-fable-5-1",
- name: "Claude Fable 5.1 (US)",
+ "us-gov.openai.gpt-oss-20b-1:0": {
+ id: "us-gov.openai.gpt-oss-20b-1:0",
+ name: "gpt-oss-20b (GovCloud)",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
reasoning: true,
- thinkingLevelMap: {"off":null,"xhigh":"xhigh","max":"max"},
- input: ["text", "image"],
+ input: ["text"],
cost: {
- input: 11,
- output: 55,
- cacheRead: 0.275,
+ input: 0.084,
+ output: 0.36,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 128000,
+ maxTokens: 16384,
+ } satisfies Model<"bedrock-converse-stream">,
+ "us.amazon.nova-2-lite-v1:0": {
+ id: "us.amazon.nova-2-lite-v1:0",
+ name: "Nova 2 Lite (US)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.33,
+ output: 2.75,
+ cacheRead: 0.0825,
+ cacheWrite: 0.33,
+ },
+ contextWindow: 1000000,
+ maxTokens: 65535,
+ } satisfies Model<"bedrock-converse-stream">,
+ "us.amazon.nova-lite-v1:0": {
+ id: "us.amazon.nova-lite-v1:0",
+ name: "Nova Lite (US)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: false,
+ input: ["text", "image"],
+ cost: {
+ input: 0.06,
+ output: 0.24,
+ cacheRead: 0.015,
+ cacheWrite: 0.06,
+ },
+ contextWindow: 300000,
+ maxTokens: 10000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "us.amazon.nova-micro-v1:0": {
+ id: "us.amazon.nova-micro-v1:0",
+ name: "Nova Micro (US)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: false,
+ input: ["text"],
+ cost: {
+ input: 0.035,
+ output: 0.14,
+ cacheRead: 0.00875,
+ cacheWrite: 0.035,
+ },
+ contextWindow: 128000,
+ maxTokens: 10000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "us.amazon.nova-premier-v1:0": {
+ id: "us.amazon.nova-premier-v1:0",
+ name: "Nova Premier (US)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: false,
+ input: ["text", "image"],
+ cost: {
+ input: 2.5,
+ output: 12.5,
+ cacheRead: 0.625,
+ cacheWrite: 2.5,
+ },
+ contextWindow: 1000000,
+ maxTokens: 10000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "us.amazon.nova-pro-v1:0": {
+ id: "us.amazon.nova-pro-v1:0",
+ name: "Nova Pro (US)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: false,
+ input: ["text", "image"],
+ cost: {
+ input: 0.8,
+ output: 3.2,
+ cacheRead: 0.2,
+ cacheWrite: 0.8,
+ },
+ contextWindow: 300000,
+ maxTokens: 10000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "us.anthropic.claude-fable-5": {
+ id: "us.anthropic.claude-fable-5",
+ name: "Claude Fable 5 (US)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"xhigh":"xhigh","max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 11,
+ output: 55,
+ cacheRead: 1.1,
+ cacheWrite: 13.75,
+ },
+ contextWindow: 1000000,
+ maxTokens: 128000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "us.anthropic.claude-fable-5-1": {
+ id: "us.anthropic.claude-fable-5-1",
+ name: "Claude Fable 5.1 (US)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"xhigh":"xhigh","max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 11,
+ output: 55,
+ cacheRead: 0.275,
cacheWrite: 13.75,
},
contextWindow: 1000000,
@@ -1791,10 +2255,10 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
- input: 1,
- output: 5,
- cacheRead: 0.1,
- cacheWrite: 1.25,
+ input: 1.1,
+ output: 5.5,
+ cacheRead: 0.11,
+ cacheWrite: 1.375,
},
contextWindow: 200000,
maxTokens: 64000,
@@ -1825,10 +2289,10 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
- input: 5,
- output: 25,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 5.5,
+ output: 27.5,
+ cacheRead: 0.55,
+ cacheWrite: 6.875,
},
contextWindow: 200000,
maxTokens: 64000,
@@ -1843,8 +2307,8 @@ export const MODELS = {
thinkingLevelMap: {"max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 25,
+ input: 5.5,
+ output: 27.5,
cacheRead: 0.5,
cacheWrite: 6.25,
},
@@ -1861,10 +2325,10 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 25,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 5.5,
+ output: 27.5,
+ cacheRead: 0.55,
+ cacheWrite: 6.875,
},
contextWindow: 1000000,
maxTokens: 128000,
@@ -1879,10 +2343,10 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 25,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 5.5,
+ output: 27.5,
+ cacheRead: 0.55,
+ cacheWrite: 6.875,
},
contextWindow: 1000000,
maxTokens: 128000,
@@ -1897,17 +2361,17 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 5,
- output: 25,
- cacheRead: 0.5,
- cacheWrite: 6.25,
+ input: 5.5,
+ output: 27.5,
+ cacheRead: 0.55,
+ cacheWrite: 6.875,
},
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
- "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
- id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
- name: "Claude Sonnet 4.5 (US)",
+ "us.anthropic.claude-sonnet-4-20250514-v1:0": {
+ id: "us.anthropic.claude-sonnet-4-20250514-v1:0",
+ name: "Claude Sonnet 4 (US)",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1922,6 +2386,23 @@ export const MODELS = {
contextWindow: 200000,
maxTokens: 64000,
} satisfies Model<"bedrock-converse-stream">,
+ "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
+ id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
+ name: "Claude Sonnet 4.5 (US)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 3.3,
+ output: 16.5,
+ cacheRead: 0.33,
+ cacheWrite: 4.125,
+ },
+ contextWindow: 200000,
+ maxTokens: 64000,
+ } satisfies Model<"bedrock-converse-stream">,
"us.anthropic.claude-sonnet-4-6": {
id: "us.anthropic.claude-sonnet-4-6",
name: "Claude Sonnet 4.6 (US)",
@@ -1932,13 +2413,13 @@ export const MODELS = {
thinkingLevelMap: {"max":"max"},
input: ["text", "image"],
cost: {
- input: 3,
- output: 15,
- cacheRead: 0.3,
- cacheWrite: 3.75,
+ input: 3.3,
+ output: 16.5,
+ cacheRead: 0.33,
+ cacheWrite: 4.125,
},
contextWindow: 1000000,
- maxTokens: 64000,
+ maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
"us.anthropic.claude-sonnet-5": {
id: "us.anthropic.claude-sonnet-5",
@@ -1950,30 +2431,64 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","max":"max"},
input: ["text", "image"],
cost: {
- input: 2,
- output: 10,
- cacheRead: 0.2,
- cacheWrite: 2.5,
+ input: 2.2,
+ output: 11,
+ cacheRead: 0.22,
+ cacheWrite: 2.75,
},
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
- "us.deepseek.r1-v1:0": {
- id: "us.deepseek.r1-v1:0",
- name: "DeepSeek-R1 (US)",
+ "us.meta.llama3-1-70b-instruct-v1:0": {
+ id: "us.meta.llama3-1-70b-instruct-v1:0",
+ name: "Llama 3.1 70B Instruct (US)",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
- reasoning: true,
+ reasoning: false,
input: ["text"],
cost: {
- input: 1.35,
- output: 5.4,
+ input: 0.72,
+ output: 0.72,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
- maxTokens: 32768,
+ maxTokens: 4096,
+ } satisfies Model<"bedrock-converse-stream">,
+ "us.meta.llama3-1-8b-instruct-v1:0": {
+ id: "us.meta.llama3-1-8b-instruct-v1:0",
+ name: "Llama 3.1 8B Instruct (US)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: false,
+ input: ["text"],
+ cost: {
+ input: 0.22,
+ output: 0.22,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 128000,
+ maxTokens: 4096,
+ } satisfies Model<"bedrock-converse-stream">,
+ "us.meta.llama3-3-70b-instruct-v1:0": {
+ id: "us.meta.llama3-3-70b-instruct-v1:0",
+ name: "Llama 3.3 70B Instruct (US)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: false,
+ input: ["text"],
+ cost: {
+ input: 0.72,
+ output: 0.72,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 128000,
+ maxTokens: 4096,
} satisfies Model<"bedrock-converse-stream">,
"us.meta.llama4-maverick-17b-instruct-v1:0": {
id: "us.meta.llama4-maverick-17b-instruct-v1:0",
@@ -1990,7 +2505,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1000000,
- maxTokens: 16384,
+ maxTokens: 8192,
} satisfies Model<"bedrock-converse-stream">,
"us.meta.llama4-scout-17b-instruct-v1:0": {
id: "us.meta.llama4-scout-17b-instruct-v1:0",
@@ -2006,53 +2521,193 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 3500000,
- maxTokens: 16384,
+ contextWindow: 10000000,
+ maxTokens: 8192,
} satisfies Model<"bedrock-converse-stream">,
- "writer.palmyra-x4-v1:0": {
- id: "writer.palmyra-x4-v1:0",
- name: "Palmyra X4",
+ "us.mistral.pixtral-large-2502-v1:0": {
+ id: "us.mistral.pixtral-large-2502-v1:0",
+ name: "Pixtral Large (25.02) (US)",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
- reasoning: true,
- input: ["text"],
+ reasoning: false,
+ input: ["text", "image"],
cost: {
- input: 2.5,
- output: 10,
+ input: 2,
+ output: 6,
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 122880,
+ contextWindow: 128000,
maxTokens: 8192,
} satisfies Model<"bedrock-converse-stream">,
- "writer.palmyra-x5-v1:0": {
- id: "writer.palmyra-x5-v1:0",
- name: "Palmyra X5",
+ "us.openai.gpt-5.6-luna": {
+ id: "us.openai.gpt-5.6-luna",
+ name: "GPT-5.6 Luna (US)",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
reasoning: true,
- input: ["text"],
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
cost: {
- input: 0.6,
- output: 6,
- cacheRead: 0,
- cacheWrite: 0,
+ input: 0.22,
+ output: 1.32,
+ cacheRead: 0.022,
+ cacheWrite: 0.275,
},
- contextWindow: 1040000,
- maxTokens: 8192,
+ contextWindow: 1050000,
+ maxTokens: 128000,
} satisfies Model<"bedrock-converse-stream">,
- "xai.grok-4.3": {
- id: "xai.grok-4.3",
- name: "Grok 4.3",
+ "us.openai.gpt-5.6-sol": {
+ id: "us.openai.gpt-5.6-sol",
+ name: "GPT-5.6 Sol (US)",
api: "bedrock-converse-stream",
provider: "amazon-bedrock",
baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 1.25,
+ input: 4.4,
+ output: 22,
+ cacheRead: 0.44,
+ cacheWrite: 5.5,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "us.openai.gpt-5.6-terra": {
+ id: "us.openai.gpt-5.6-terra",
+ name: "GPT-5.6 Terra (US)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 2.2,
+ output: 13.2,
+ cacheRead: 0.22,
+ cacheWrite: 2.75,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "us.openai.gpt-6-astra": {
+ id: "us.openai.gpt-6-astra",
+ name: "GPT-6 Astra (US)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"xhigh":"xhigh","max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 11,
+ output: 55,
+ cacheRead: 1.1,
+ cacheWrite: 13.75,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "us.writer.palmyra-x4-v1:0": {
+ id: "us.writer.palmyra-x4-v1:0",
+ name: "Palmyra X4 (US)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 2.5,
+ output: 10,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 122880,
+ maxTokens: 8192,
+ } satisfies Model<"bedrock-converse-stream">,
+ "us.writer.palmyra-x5-v1:0": {
+ id: "us.writer.palmyra-x5-v1:0",
+ name: "Palmyra X5 (US)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0.6,
+ output: 6,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 1040000,
+ maxTokens: 8192,
+ } satisfies Model<"bedrock-converse-stream">,
+ "us.xai.grok-4.6": {
+ id: "us.xai.grok-4.6",
+ name: "Grok 4.6 (US)",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 2.2,
+ output: 6.6,
+ cacheRead: 0.55,
+ cacheWrite: 0,
+ },
+ contextWindow: 500000,
+ maxTokens: 500000,
+ } satisfies Model<"bedrock-converse-stream">,
+ "writer.palmyra-x4-v1:0": {
+ id: "writer.palmyra-x4-v1:0",
+ name: "Palmyra X4",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 2.5,
+ output: 10,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 122880,
+ maxTokens: 8192,
+ } satisfies Model<"bedrock-converse-stream">,
+ "writer.palmyra-x5-v1:0": {
+ id: "writer.palmyra-x5-v1:0",
+ name: "Palmyra X5",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0.6,
+ output: 6,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 1040000,
+ maxTokens: 8192,
+ } satisfies Model<"bedrock-converse-stream">,
+ "xai.grok-4.3": {
+ id: "xai.grok-4.3",
+ name: "Grok 4.3",
+ api: "bedrock-converse-stream",
+ provider: "amazon-bedrock",
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 1.25,
output: 2.5,
cacheRead: 0.2,
cacheWrite: 0,
@@ -2126,7 +2781,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 202752,
- maxTokens: 101376,
+ maxTokens: 131072,
} satisfies Model<"bedrock-converse-stream">,
},
"anthropic": {
@@ -3119,39 +3774,39 @@ export const MODELS = {
} satisfies Model<"azure-openai-responses">,
},
"cerebras": {
- "gemma-4-31b": {
- id: "gemma-4-31b",
- name: "Gemma 4 31B IT",
+ "gpt-oss-120b": {
+ id: "gpt-oss-120b",
+ name: "GPT OSS 120B",
api: "openai-completions",
provider: "cerebras",
baseUrl: "https://api.cerebras.ai/v1",
reasoning: true,
- input: ["text", "image"],
+ input: ["text"],
cost: {
- input: 0.99,
- output: 1.49,
+ input: 0.35,
+ output: 0.75,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 40960,
} satisfies Model<"openai-completions">,
- "gpt-oss-120b": {
- id: "gpt-oss-120b",
- name: "GPT OSS 120B",
+ "qwen-3.8-27b": {
+ id: "qwen-3.8-27b",
+ name: "Qwen3.8 27B",
api: "openai-completions",
provider: "cerebras",
baseUrl: "https://api.cerebras.ai/v1",
reasoning: true,
- input: ["text"],
+ input: ["text", "image"],
cost: {
- input: 0.35,
- output: 0.75,
+ input: 0.99,
+ output: 1.49,
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 131072,
- maxTokens: 40960,
+ contextWindow: 65536,
+ maxTokens: 32768,
} satisfies Model<"openai-completions">,
},
"cloudflare-ai-gateway": {
@@ -3669,6 +4324,24 @@ export const MODELS = {
contextWindow: 1050000,
maxTokens: 128000,
} satisfies Model<"openai-responses">,
+ "gpt-6-astra": {
+ id: "gpt-6-astra",
+ name: "GPT-6 Astra",
+ api: "openai-responses",
+ provider: "cloudflare-ai-gateway",
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"xhigh":"xhigh","max":"max","off":null},
+ input: ["text", "image"],
+ cost: {
+ input: 10,
+ output: 50,
+ cacheRead: 1,
+ cacheWrite: 12,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-responses">,
"o3": {
id: "o3",
name: "o3",
@@ -4028,7 +4701,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1310720,
- maxTokens: 1310720,
+ maxTokens: 1048576,
} satisfies Model<"openai-completions">,
"@cf/zai-org/glm-5.3-flash": {
id: "@cf/zai-org/glm-5.3-flash",
@@ -4124,6 +4797,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 384000,
} satisfies Model<"anthropic-messages">,
+ "accounts/fireworks/models/deepseek-v4-pro": {
+ id: "accounts/fireworks/models/deepseek-v4-pro",
+ name: "DeepSeek V4 Pro",
+ api: "anthropic-messages",
+ provider: "fireworks",
+ baseUrl: "https://api.fireworks.ai/inference",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 1.2,
+ output: 1.2,
+ cacheRead: 0.6,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 384000,
+ } satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/deepseek-v4-pro-0813": {
id: "accounts/fireworks/models/deepseek-v4-pro-0813",
name: "DeepSeek V4 Pro 0813",
@@ -4141,6 +4831,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 384000,
} satisfies Model<"anthropic-messages">,
+ "accounts/fireworks/models/deepseek-v4p1-flash": {
+ id: "accounts/fireworks/models/deepseek-v4p1-flash",
+ name: "DeepSeek V4.1 Flash",
+ api: "anthropic-messages",
+ provider: "fireworks",
+ baseUrl: "https://api.fireworks.ai/inference",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.22,
+ output: 0.66,
+ cacheRead: 0.007,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 384000,
+ } satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/glm-5p2": {
id: "accounts/fireworks/models/glm-5p2",
name: "GLM 5.2",
@@ -4172,8 +4879,8 @@ export const MODELS = {
cacheRead: 0.26,
cacheWrite: 0,
},
- contextWindow: 1000000,
- maxTokens: 131072,
+ contextWindow: 1048573,
+ maxTokens: 262144,
} satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/glm-5p3-flash": {
id: "accounts/fireworks/models/glm-5p3-flash",
@@ -4189,7 +4896,7 @@ export const MODELS = {
cacheRead: 0.03,
cacheWrite: 0,
},
- contextWindow: 1000000,
+ contextWindow: 1048573,
maxTokens: 131072,
} satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/gpt-oss-120b": {
@@ -4278,6 +4985,23 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 131072,
} satisfies Model<"anthropic-messages">,
+ "accounts/fireworks/models/minimax-m2p7": {
+ id: "accounts/fireworks/models/minimax-m2p7",
+ name: "MiniMax-M2.7",
+ api: "anthropic-messages",
+ provider: "fireworks",
+ baseUrl: "https://api.fireworks.ai/inference",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 1.2,
+ output: 1.2,
+ cacheRead: 0.6,
+ cacheWrite: 0,
+ },
+ contextWindow: 196608,
+ maxTokens: 131072,
+ } satisfies Model<"anthropic-messages">,
"accounts/fireworks/models/minimax-m3": {
id: "accounts/fireworks/models/minimax-m3",
name: "MiniMax-M3",
@@ -4285,7 +5009,7 @@ export const MODELS = {
provider: "fireworks",
baseUrl: "https://api.fireworks.ai/inference",
reasoning: true,
- input: ["text", "image"],
+ input: ["text"],
cost: {
input: 0.3,
output: 1.2,
@@ -4323,7 +5047,7 @@ export const MODELS = {
cost: {
input: 0.6,
output: 2.4,
- cacheRead: 0.119,
+ cacheRead: 0.12,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -4387,7 +5111,7 @@ export const MODELS = {
provider: "fireworks",
baseUrl: "https://api.fireworks.ai/inference",
reasoning: true,
- input: ["text"],
+ input: ["text", "image"],
cost: {
input: 2,
output: 6,
@@ -4397,6 +5121,40 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 131072,
} satisfies Model<"anthropic-messages">,
+ "accounts/fireworks/routers/deepseek-flash-latest": {
+ id: "accounts/fireworks/routers/deepseek-flash-latest",
+ name: "DeepSeek Flash Latest",
+ api: "anthropic-messages",
+ provider: "fireworks",
+ baseUrl: "https://api.fireworks.ai/inference",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.22,
+ output: 0.66,
+ cacheRead: 0.007,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 384000,
+ } satisfies Model<"anthropic-messages">,
+ "accounts/fireworks/routers/deepseek-pro-latest": {
+ id: "accounts/fireworks/routers/deepseek-pro-latest",
+ name: "DeepSeek Pro Latest",
+ api: "anthropic-messages",
+ provider: "fireworks",
+ baseUrl: "https://api.fireworks.ai/inference",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 1.32,
+ output: 3.96,
+ cacheRead: 0.044,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 384000,
+ } satisfies Model<"anthropic-messages">,
"accounts/fireworks/routers/glm-5p2-fast": {
id: "accounts/fireworks/routers/glm-5p2-fast",
name: "GLM 5.2 Fast",
@@ -4414,15 +5172,100 @@ export const MODELS = {
contextWindow: 1048575,
maxTokens: 131072,
} satisfies Model<"anthropic-messages">,
- "accounts/fireworks/routers/kimi-k3-fast": {
- id: "accounts/fireworks/routers/kimi-k3-fast",
- name: "Kimi K3 Fast",
+ "accounts/fireworks/routers/glm-5p3-fast": {
+ id: "accounts/fireworks/routers/glm-5p3-fast",
+ name: "GLM 5.3 Fast",
api: "anthropic-messages",
provider: "fireworks",
baseUrl: "https://api.fireworks.ai/inference",
reasoning: true,
- thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":null,"xhigh":null,"max":"max"},
- input: ["text", "image"],
+ input: ["text"],
+ cost: {
+ input: 2.1,
+ output: 6.6,
+ cacheRead: 0.39,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048572,
+ maxTokens: 262144,
+ } satisfies Model<"anthropic-messages">,
+ "accounts/fireworks/routers/glm-fast-latest": {
+ id: "accounts/fireworks/routers/glm-fast-latest",
+ name: "GLM 5.3 Fast (Latest)",
+ api: "anthropic-messages",
+ provider: "fireworks",
+ baseUrl: "https://api.fireworks.ai/inference",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 2.1,
+ output: 6.6,
+ cacheRead: 0.39,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048572,
+ maxTokens: 262144,
+ } satisfies Model<"anthropic-messages">,
+ "accounts/fireworks/routers/glm-flash-latest": {
+ id: "accounts/fireworks/routers/glm-flash-latest",
+ name: "GLM Flash Latest (GLM 5.3 Flash)",
+ api: "anthropic-messages",
+ provider: "fireworks",
+ baseUrl: "https://api.fireworks.ai/inference",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.15,
+ output: 0.5,
+ cacheRead: 0.03,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048573,
+ maxTokens: 131072,
+ } satisfies Model<"anthropic-messages">,
+ "accounts/fireworks/routers/glm-latest": {
+ id: "accounts/fireworks/routers/glm-latest",
+ name: "GLM Latest",
+ api: "anthropic-messages",
+ provider: "fireworks",
+ baseUrl: "https://api.fireworks.ai/inference",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 1.4,
+ output: 4.4,
+ cacheRead: 0.26,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048573,
+ maxTokens: 262144,
+ } satisfies Model<"anthropic-messages">,
+ "accounts/fireworks/routers/kimi-fast-latest": {
+ id: "accounts/fireworks/routers/kimi-fast-latest",
+ name: "Kimi Fast Latest",
+ api: "anthropic-messages",
+ provider: "fireworks",
+ baseUrl: "https://api.fireworks.ai/inference",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 4.5,
+ output: 22.5,
+ cacheRead: 0.45,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
+ maxTokens: 131072,
+ } satisfies Model<"anthropic-messages">,
+ "accounts/fireworks/routers/kimi-k3-fast": {
+ id: "accounts/fireworks/routers/kimi-k3-fast",
+ name: "Kimi K3 Fast",
+ api: "anthropic-messages",
+ provider: "fireworks",
+ baseUrl: "https://api.fireworks.ai/inference",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":null,"xhigh":null,"max":"max"},
+ input: ["text", "image"],
cost: {
input: 4.5,
output: 22.5,
@@ -4432,6 +5275,57 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 131072,
} satisfies Model<"anthropic-messages">,
+ "accounts/fireworks/routers/kimi-latest": {
+ id: "accounts/fireworks/routers/kimi-latest",
+ name: "Kimi Latest",
+ api: "anthropic-messages",
+ provider: "fireworks",
+ baseUrl: "https://api.fireworks.ai/inference",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 3,
+ output: 15,
+ cacheRead: 0.3,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
+ maxTokens: 131072,
+ } satisfies Model<"anthropic-messages">,
+ "accounts/fireworks/routers/minimax-latest": {
+ id: "accounts/fireworks/routers/minimax-latest",
+ name: "MiniMax Latest",
+ api: "anthropic-messages",
+ provider: "fireworks",
+ baseUrl: "https://api.fireworks.ai/inference",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0.3,
+ output: 1.2,
+ cacheRead: 0.06,
+ cacheWrite: 0,
+ },
+ contextWindow: 512000,
+ maxTokens: 512000,
+ } satisfies Model<"anthropic-messages">,
+ "accounts/fireworks/routers/qwen-max-latest": {
+ id: "accounts/fireworks/routers/qwen-max-latest",
+ name: "Qwen Max Latest (Qwen3.8 Max)",
+ api: "anthropic-messages",
+ provider: "fireworks",
+ baseUrl: "https://api.fireworks.ai/inference",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 2,
+ output: 6,
+ cacheRead: 0.25,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 131072,
+ } satisfies Model<"anthropic-messages">,
},
"github-copilot": {
"claude-fable-5": {
@@ -6358,6 +7252,78 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 384000,
} satisfies Model<"openai-completions">,
+ "deepseek-ai/DeepSeek-V4.1-Flash": {
+ id: "deepseek-ai/DeepSeek-V4.1-Flash",
+ name: "DeepSeek V4.1 Flash",
+ api: "openai-completions",
+ provider: "huggingface",
+ baseUrl: "https://router.huggingface.co/v1",
+ compat: {"supportsDeveloperRole":false},
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.3,
+ output: 1.2,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
+ maxTokens: 384000,
+ } satisfies Model<"openai-completions">,
+ "google/gemma-3-12b-it": {
+ id: "google/gemma-3-12b-it",
+ name: "Gemma 3 12B IT",
+ api: "openai-completions",
+ provider: "huggingface",
+ baseUrl: "https://router.huggingface.co/v1",
+ compat: {"supportsDeveloperRole":false},
+ reasoning: false,
+ input: ["text", "image"],
+ cost: {
+ input: 0.05,
+ output: 0.15,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 131072,
+ maxTokens: 131072,
+ } satisfies Model<"openai-completions">,
+ "google/gemma-3-27b-it": {
+ id: "google/gemma-3-27b-it",
+ name: "Gemma 3 27B IT",
+ api: "openai-completions",
+ provider: "huggingface",
+ baseUrl: "https://router.huggingface.co/v1",
+ compat: {"supportsDeveloperRole":false},
+ reasoning: false,
+ input: ["text", "image"],
+ cost: {
+ input: 0.08,
+ output: 0.16,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 131072,
+ maxTokens: 131072,
+ } satisfies Model<"openai-completions">,
+ "google/gemma-3-4b-it": {
+ id: "google/gemma-3-4b-it",
+ name: "Gemma 3 4B IT",
+ api: "openai-completions",
+ provider: "huggingface",
+ baseUrl: "https://router.huggingface.co/v1",
+ compat: {"supportsDeveloperRole":false},
+ reasoning: false,
+ input: ["text", "image"],
+ cost: {
+ input: 0.05,
+ output: 0.1,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 131072,
+ maxTokens: 131072,
+ } satisfies Model<"openai-completions">,
"google/gemma-4-26B-A4B-it": {
id: "google/gemma-4-26B-A4B-it",
name: "Gemma 4 26B A4B IT",
@@ -6647,6 +7613,24 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
+ "tencent/Hy4-preview": {
+ id: "tencent/Hy4-preview",
+ name: "Hy4 preview",
+ api: "openai-completions",
+ provider: "huggingface",
+ baseUrl: "https://router.huggingface.co/v1",
+ compat: {"supportsDeveloperRole":false},
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0.834,
+ output: 2.501,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 64000,
+ } satisfies Model<"openai-completions">,
"thinkingmachines/Inkling": {
id: "thinkingmachines/Inkling",
name: "Inkling",
@@ -7593,173 +8577,82 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 131072,
} satisfies Model<"mistral-conversations">,
- },
- "moonshotai": {
- "kimi-k2-0711-preview": {
- id: "kimi-k2-0711-preview",
- name: "Kimi K2 0711",
- api: "openai-completions",
- provider: "moonshotai",
- baseUrl: "https://api.moonshot.ai/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: false,
+ "zai-glm-5-3": {
+ id: "zai-glm-5-3",
+ name: "GLM-5.3",
+ api: "mistral-conversations",
+ provider: "mistral",
+ baseUrl: "https://api.mistral.ai",
+ reasoning: true,
input: ["text"],
cost: {
- input: 0.6,
- output: 2.5,
- cacheRead: 0.15,
+ input: 1.4,
+ output: 4.4,
+ cacheRead: 0.14,
cacheWrite: 0,
},
- contextWindow: 131072,
- maxTokens: 16384,
- } satisfies Model<"openai-completions">,
- "kimi-k2-0905-preview": {
- id: "kimi-k2-0905-preview",
- name: "Kimi K2 0905",
+ contextWindow: 1000000,
+ maxTokens: 131072,
+ } satisfies Model<"mistral-conversations">,
+ },
+ "moonshotai": {
+ "kimi-k2.6": {
+ id: "kimi-k2.6",
+ name: "Kimi K2.6",
api: "openai-completions",
provider: "moonshotai",
baseUrl: "https://api.moonshot.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: false,
- input: ["text"],
+ reasoning: true,
+ input: ["text", "image"],
cost: {
- input: 0.6,
- output: 2.5,
- cacheRead: 0.15,
+ input: 0.95,
+ output: 4,
+ cacheRead: 0.16,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
- "kimi-k2-thinking": {
- id: "kimi-k2-thinking",
- name: "Kimi K2 Thinking",
+ "kimi-k2.7-code": {
+ id: "kimi-k2.7-code",
+ name: "Kimi K2.7 Code",
api: "openai-completions",
provider: "moonshotai",
baseUrl: "https://api.moonshot.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
reasoning: true,
- input: ["text"],
+ input: ["text", "image"],
cost: {
- input: 0.6,
- output: 2.5,
- cacheRead: 0.15,
+ input: 0.95,
+ output: 4,
+ cacheRead: 0.19,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
- "kimi-k2-thinking-turbo": {
- id: "kimi-k2-thinking-turbo",
- name: "Kimi K2 Thinking Turbo",
+ "kimi-k2.7-code-highspeed": {
+ id: "kimi-k2.7-code-highspeed",
+ name: "Kimi K2.7 Code HighSpeed",
api: "openai-completions",
provider: "moonshotai",
baseUrl: "https://api.moonshot.ai/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
reasoning: true,
- input: ["text"],
+ input: ["text", "image"],
cost: {
- input: 1.15,
+ input: 1.9,
output: 8,
- cacheRead: 0.15,
+ cacheRead: 0.38,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
- "kimi-k2-turbo-preview": {
- id: "kimi-k2-turbo-preview",
- name: "Kimi K2 Turbo",
- api: "openai-completions",
- provider: "moonshotai",
- baseUrl: "https://api.moonshot.ai/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: false,
- input: ["text"],
- cost: {
- input: 2.4,
- output: 10,
- cacheRead: 0.6,
- cacheWrite: 0,
- },
- contextWindow: 262144,
- maxTokens: 262144,
- } satisfies Model<"openai-completions">,
- "kimi-k2.5": {
- id: "kimi-k2.5",
- name: "Kimi K2.5",
- api: "openai-completions",
- provider: "moonshotai",
- baseUrl: "https://api.moonshot.ai/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 0.6,
- output: 3,
- cacheRead: 0.1,
- cacheWrite: 0,
- },
- contextWindow: 262144,
- maxTokens: 262144,
- } satisfies Model<"openai-completions">,
- "kimi-k2.6": {
- id: "kimi-k2.6",
- name: "Kimi K2.6",
- api: "openai-completions",
- provider: "moonshotai",
- baseUrl: "https://api.moonshot.ai/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 0.95,
- output: 4,
- cacheRead: 0.16,
- cacheWrite: 0,
- },
- contextWindow: 262144,
- maxTokens: 262144,
- } satisfies Model<"openai-completions">,
- "kimi-k2.7-code": {
- id: "kimi-k2.7-code",
- name: "Kimi K2.7 Code",
- api: "openai-completions",
- provider: "moonshotai",
- baseUrl: "https://api.moonshot.ai/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 0.95,
- output: 4,
- cacheRead: 0.19,
- cacheWrite: 0,
- },
- contextWindow: 262144,
- maxTokens: 262144,
- } satisfies Model<"openai-completions">,
- "kimi-k2.7-code-highspeed": {
- id: "kimi-k2.7-code-highspeed",
- name: "Kimi K2.7 Code HighSpeed",
- api: "openai-completions",
- provider: "moonshotai",
- baseUrl: "https://api.moonshot.ai/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 1.9,
- output: 8,
- cacheRead: 0.38,
- cacheWrite: 0,
- },
- contextWindow: 262144,
- maxTokens: 262144,
- } satisfies Model<"openai-completions">,
- "kimi-k3": {
- id: "kimi-k3",
- name: "Kimi K3",
+ "kimi-k3": {
+ id: "kimi-k3",
+ name: "Kimi K3",
api: "openai-completions",
provider: "moonshotai",
baseUrl: "https://api.moonshot.ai/v1",
@@ -7778,114 +8671,6 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
},
"moonshotai-cn": {
- "kimi-k2-0711-preview": {
- id: "kimi-k2-0711-preview",
- name: "Kimi K2 0711",
- api: "openai-completions",
- provider: "moonshotai-cn",
- baseUrl: "https://api.moonshot.cn/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: false,
- input: ["text"],
- cost: {
- input: 0.6,
- output: 2.5,
- cacheRead: 0.15,
- cacheWrite: 0,
- },
- contextWindow: 131072,
- maxTokens: 16384,
- } satisfies Model<"openai-completions">,
- "kimi-k2-0905-preview": {
- id: "kimi-k2-0905-preview",
- name: "Kimi K2 0905",
- api: "openai-completions",
- provider: "moonshotai-cn",
- baseUrl: "https://api.moonshot.cn/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: false,
- input: ["text"],
- cost: {
- input: 0.6,
- output: 2.5,
- cacheRead: 0.15,
- cacheWrite: 0,
- },
- contextWindow: 262144,
- maxTokens: 262144,
- } satisfies Model<"openai-completions">,
- "kimi-k2-thinking": {
- id: "kimi-k2-thinking",
- name: "Kimi K2 Thinking",
- api: "openai-completions",
- provider: "moonshotai-cn",
- baseUrl: "https://api.moonshot.cn/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: true,
- input: ["text"],
- cost: {
- input: 0.6,
- output: 2.5,
- cacheRead: 0.15,
- cacheWrite: 0,
- },
- contextWindow: 262144,
- maxTokens: 262144,
- } satisfies Model<"openai-completions">,
- "kimi-k2-thinking-turbo": {
- id: "kimi-k2-thinking-turbo",
- name: "Kimi K2 Thinking Turbo",
- api: "openai-completions",
- provider: "moonshotai-cn",
- baseUrl: "https://api.moonshot.cn/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: true,
- input: ["text"],
- cost: {
- input: 1.15,
- output: 8,
- cacheRead: 0.15,
- cacheWrite: 0,
- },
- contextWindow: 262144,
- maxTokens: 262144,
- } satisfies Model<"openai-completions">,
- "kimi-k2-turbo-preview": {
- id: "kimi-k2-turbo-preview",
- name: "Kimi K2 Turbo",
- api: "openai-completions",
- provider: "moonshotai-cn",
- baseUrl: "https://api.moonshot.cn/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: false,
- input: ["text"],
- cost: {
- input: 2.4,
- output: 10,
- cacheRead: 0.6,
- cacheWrite: 0,
- },
- contextWindow: 262144,
- maxTokens: 262144,
- } satisfies Model<"openai-completions">,
- "kimi-k2.5": {
- id: "kimi-k2.5",
- name: "Kimi K2.5",
- api: "openai-completions",
- provider: "moonshotai-cn",
- baseUrl: "https://api.moonshot.cn/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 0.6,
- output: 3,
- cacheRead: 0.1,
- cacheWrite: 0,
- },
- contextWindow: 262144,
- maxTokens: 262144,
- } satisfies Model<"openai-completions">,
"kimi-k2.6": {
id: "kimi-k2.6",
name: "Kimi K2.6",
@@ -9240,6 +10025,25 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 384000,
} satisfies Model<"openai-completions">,
+ "deepseek-v4.1-flash": {
+ id: "deepseek-v4.1-flash",
+ name: "DeepSeek V4.1 Flash",
+ api: "openai-completions",
+ provider: "opencode",
+ baseUrl: "https://opencode.ai/zen/v1",
+ compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 0.3,
+ output: 1.2,
+ cacheRead: 0.006,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 384000,
+ } satisfies Model<"openai-completions">,
"gemini-3-flash": {
id: "gemini-3-flash",
name: "Gemini 3 Flash",
@@ -9759,7 +10563,7 @@ export const MODELS = {
} satisfies Model<"openai-responses">,
"gpt-5.6-sol": {
id: "gpt-5.6-sol",
- name: "GPT-5.6 Sol (50% Off)",
+ name: "GPT-5.6 Sol",
api: "openai-responses",
provider: "opencode",
baseUrl: "https://opencode.ai/zen/v1",
@@ -9767,10 +10571,10 @@ export const MODELS = {
thinkingLevelMap: {"off":null,"xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 2,
- output: 10,
- cacheRead: 0.2,
- cacheWrite: 2.5,
+ input: 4,
+ output: 20,
+ cacheRead: 0.4,
+ cacheWrite: 5,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -10152,6 +10956,23 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"anthropic-messages">,
+ "qwen3.8-flash": {
+ id: "qwen3.8-flash",
+ name: "Qwen3.8 Flash",
+ api: "anthropic-messages",
+ provider: "opencode",
+ baseUrl: "https://opencode.ai/zen",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.15,
+ output: 0.47,
+ cacheRead: 0.016,
+ cacheWrite: 0.2,
+ },
+ contextWindow: 1000000,
+ maxTokens: 131072,
+ } satisfies Model<"anthropic-messages">,
},
"opencode-go": {
"deepseek-v4-flash": {
@@ -10165,9 +10986,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.22,
- output: 0.66,
- cacheRead: 0.007,
+ input: 0.15,
+ output: 0.6,
+ cacheRead: 0.003,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -10184,9 +11005,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text", "image"],
cost: {
- input: 0.22,
- output: 0.66,
- cacheRead: 0.007,
+ input: 0.15,
+ output: 0.6,
+ cacheRead: 0.003,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -10211,6 +11032,25 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 384000,
} satisfies Model<"openai-completions">,
+ "deepseek-v4.1-flash": {
+ id: "deepseek-v4.1-flash",
+ name: "DeepSeek V4.1 Flash",
+ api: "openai-completions",
+ provider: "opencode-go",
+ baseUrl: "https://opencode.ai/zen/go/v1",
+ compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 0.15,
+ output: 0.6,
+ cacheRead: 0.003,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 384000,
+ } satisfies Model<"openai-completions">,
"glm-5.1": {
id: "glm-5.1",
name: "GLM-5.1",
@@ -10264,16 +11104,16 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"glm-5.3-flash": {
id: "glm-5.3-flash",
- name: "GLM-5.3-Flash (2x usage)",
+ name: "GLM-5.3-Flash",
api: "openai-completions",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go/v1",
reasoning: true,
input: ["text", "image"],
cost: {
- input: 0.075,
- output: 0.25,
- cacheRead: 0.015,
+ input: 0.15,
+ output: 0.5,
+ cacheRead: 0.03,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -10314,8 +11154,25 @@ export const MODELS = {
contextWindow: 500000,
maxTokens: 500000,
} satisfies Model<"openai-responses">,
- "hy3": {
- id: "hy3",
+ "grok-4.7": {
+ id: "grok-4.7",
+ name: "Grok 4.7",
+ api: "openai-responses",
+ provider: "opencode-go",
+ baseUrl: "https://opencode.ai/zen/go/v1",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 2,
+ output: 6,
+ cacheRead: 0.5,
+ cacheWrite: 0,
+ },
+ contextWindow: 500000,
+ maxTokens: 500000,
+ } satisfies Model<"openai-responses">,
+ "hy3": {
+ id: "hy3",
name: "Hy3",
api: "openai-completions",
provider: "opencode-go",
@@ -10463,7 +11320,7 @@ export const MODELS = {
input: 0.3,
output: 1.2,
cacheRead: 0.06,
- cacheWrite: 0,
+ cacheWrite: 0.375,
},
contextWindow: 204800,
maxTokens: 131072,
@@ -10519,23 +11376,6 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 131072,
} satisfies Model<"openai-responses">,
- "omen-alpha": {
- id: "omen-alpha",
- name: "Omen Alpha",
- api: "openai-completions",
- provider: "opencode-go",
- baseUrl: "https://opencode.ai/zen/go/v1",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 0.2,
- output: 0.66,
- cacheRead: 0.04,
- cacheWrite: 0,
- },
- contextWindow: 500000,
- maxTokens: 128000,
- } satisfies Model<"openai-completions">,
"qwen3.6-plus": {
id: "qwen3.6-plus",
name: "Qwen3.6 Plus",
@@ -10840,25 +11680,6 @@ export const MODELS = {
contextWindow: 200000,
maxTokens: 64000,
} satisfies Model<"openai-completions">,
- "anthropic/claude-opus-4": {
- id: "anthropic/claude-opus-4",
- name: "Anthropic: Claude Opus 4",
- api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- compat: {"supportsReasoningEffort":false},
- reasoning: true,
- thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
- input: ["text", "image"],
- cost: {
- input: 15,
- output: 75,
- cacheRead: 1.5,
- cacheWrite: 18.75,
- },
- contextWindow: 200000,
- maxTokens: 32000,
- } satisfies Model<"openai-completions">,
"anthropic/claude-opus-4.1": {
id: "anthropic/claude-opus-4.1",
name: "Anthropic: Claude Opus 4.1",
@@ -10953,7 +11774,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"anthropic/claude-opus-5": {
id: "anthropic/claude-opus-5",
- name: "Claude Opus 5",
+ name: "Anthropic: Claude Opus 5",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
@@ -10985,7 +11806,7 @@ export const MODELS = {
cacheRead: 0.3,
cacheWrite: 3.75,
},
- contextWindow: 1000000,
+ contextWindow: 200000,
maxTokens: 64000,
} satisfies Model<"openai-completions">,
"anthropic/claude-sonnet-4.5": {
@@ -11288,13 +12109,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.55,
- output: 1.6500000000000001,
- cacheRead: 0.55,
+ input: 0.25,
+ output: 0.95,
+ cacheRead: 0.13,
cacheWrite: 0,
},
contextWindow: 163840,
- maxTokens: 144900,
+ maxTokens: 32768,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-r1": {
id: "deepseek/deepseek-r1",
@@ -11402,9 +12223,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.08106,
- output: 0.16212,
- cacheRead: 0.016212,
+ input: 0.055439999999999996,
+ output: 0.11087999999999999,
+ cacheRead: 0.011087999999999999,
cacheWrite: 0,
},
contextWindow: 1048576,
@@ -11421,13 +12242,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.049980000000000004,
- output: 0.09996000000000001,
- cacheRead: 0.009996000000000001,
+ input: 0.04,
+ output: 0.16,
+ cacheRead: 0.016,
cacheWrite: 0,
},
contextWindow: 1310720,
- maxTokens: 131072,
+ maxTokens: 943718,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-flash-vision-exp": {
id: "deepseek/deepseek-v4-flash-vision-exp",
@@ -11440,13 +12261,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text", "image"],
cost: {
- input: 0.44,
- output: 1.32,
- cacheRead: 0.014,
+ input: 0.22,
+ output: 0.66,
+ cacheRead: 0.007,
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 384000,
+ maxTokens: 943718,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-pro": {
id: "deepseek/deepseek-v4-pro",
@@ -11459,9 +12280,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.7078319999999999,
- output: 1.4156639999999998,
- cacheRead: 0.058986000000000004,
+ input: 0.927768,
+ output: 1.855536,
+ cacheRead: 0.077314,
cacheWrite: 0,
},
contextWindow: 1048576,
@@ -11478,9 +12299,28 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 1.12068,
- output: 3.36204,
- cacheRead: 0.037356,
+ input: 0.57024,
+ output: 1.7107199999999998,
+ cacheRead: 0.019008,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
+ maxTokens: 384000,
+ } satisfies Model<"openai-completions">,
+ "deepseek/deepseek-v4.1-flash": {
+ id: "deepseek/deepseek-v4.1-flash",
+ name: "DeepSeek: DeepSeek V4.1 Flash",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 0.3,
+ output: 1.2,
+ cacheRead: 0.006,
cacheWrite: 0,
},
contextWindow: 1048576,
@@ -11581,25 +12421,6 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
- "google/gemini-2.5-pro-preview-05-06": {
- id: "google/gemini-2.5-pro-preview-05-06",
- name: "Google: Gemini 2.5 Pro Preview 05-06",
- api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- compat: {"supportsReasoningEffort":false},
- reasoning: true,
- thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
- input: ["text", "image"],
- cost: {
- input: 1.25,
- output: 10,
- cacheRead: 0.125,
- cacheWrite: 0.375,
- },
- contextWindow: 1048576,
- maxTokens: 65535,
- } satisfies Model<"openai-completions">,
"google/gemini-3-flash-preview": {
id: "google/gemini-3-flash-preview",
name: "Google: Gemini 3 Flash Preview",
@@ -11844,13 +12665,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.07,
- output: 0.33999999999999997,
- cacheRead: 0,
+ input: 0.09,
+ output: 0.3,
+ cacheRead: 0.049999999999999996,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 16384,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"google/gemma-4-26b-a4b-it:free": {
id: "google/gemma-4-26b-a4b-it:free",
@@ -11919,9 +12740,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.09999999999999999,
- output: 0.15,
- cacheRead: 0.049999999999999996,
+ input: 0.06,
+ output: 0.25,
+ cacheRead: 0.015,
cacheWrite: 0,
},
contextWindow: 131072,
@@ -11945,9 +12766,9 @@ export const MODELS = {
contextWindow: 128000,
maxTokens: 50000,
} satisfies Model<"openai-completions">,
- "inception/mercury-2.5-preview": {
- id: "inception/mercury-2.5-preview",
- name: "Inception: Mercury 2.5 Preview",
+ "inception/mercury-2.5": {
+ id: "inception/mercury-2.5",
+ name: "Inception: Mercury 2.5",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
@@ -12039,6 +12860,44 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
+ "inclusionai/ling-3.0-flash-vl": {
+ id: "inclusionai/ling-3.0-flash-vl",
+ name: "inclusionAI: Ling 3.0 Flash VL",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ compat: {"supportsReasoningEffort":false},
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 0.06,
+ output: 0.18,
+ cacheRead: 0.012,
+ cacheWrite: 0,
+ },
+ contextWindow: 131072,
+ maxTokens: 32768,
+ } satisfies Model<"openai-completions">,
+ "inclusionai/ling-3.0-flash-vl:free": {
+ id: "inclusionai/ling-3.0-flash-vl:free",
+ name: "inclusionAI: Ling 3.0 Flash VL (free)",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ compat: {"supportsReasoningEffort":false},
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 0,
+ output: 0,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 32768,
+ } satisfies Model<"openai-completions">,
"kwaipilot/kat-coder-pro-v2": {
id: "kwaipilot/kat-coder-pro-v2",
name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -12172,12 +13031,12 @@ export const MODELS = {
input: ["text", "image"],
cost: {
input: 0.19999999999999998,
- output: 0.696,
+ output: 0.7999999999999999,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 115200,
+ maxTokens: 16384,
} satisfies Model<"openai-completions">,
"meta-llama/llama-4-scout": {
id: "meta-llama/llama-4-scout",
@@ -12207,12 +13066,12 @@ export const MODELS = {
input: ["text", "image"],
cost: {
input: 0.3,
- output: 1.1,
+ output: 1.2,
cacheRead: 0.04,
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 117964,
+ maxTokens: 16384,
} satisfies Model<"openai-completions">,
"meta/muse-spark-1.1": {
id: "meta/muse-spark-1.1",
@@ -12315,7 +13174,7 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.55,
+ input: 0.39999999999999997,
output: 2.2,
cacheRead: 0,
cacheWrite: 0,
@@ -12399,25 +13258,6 @@ export const MODELS = {
contextWindow: 204800,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
- "minimax/minimax-m2.7:free": {
- id: "minimax/minimax-m2.7:free",
- name: "MiniMax: MiniMax M2.7 (free)",
- api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- compat: {"supportsReasoningEffort":false},
- reasoning: true,
- thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
- input: ["text"],
- cost: {
- input: 0,
- output: 0,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 196608,
- maxTokens: 176947,
- } satisfies Model<"openai-completions">,
"minimax/minimax-m3": {
id: "minimax/minimax-m3",
name: "MiniMax: MiniMax M3",
@@ -12437,25 +13277,6 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 512000,
} satisfies Model<"openai-completions">,
- "minimax/minimax-m3:free": {
- id: "minimax/minimax-m3:free",
- name: "MiniMax: MiniMax M3 (free)",
- api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- compat: {"supportsReasoningEffort":false},
- reasoning: true,
- thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
- input: ["text", "image"],
- cost: {
- input: 0,
- output: 0,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 1048576,
- maxTokens: 943718,
- } satisfies Model<"openai-completions">,
"mistralai/codestral-2508": {
id: "mistralai/codestral-2508",
name: "Mistral: Codestral 2508",
@@ -12575,23 +13396,6 @@ export const MODELS = {
contextWindow: 131072,
maxTokens: 104857,
} satisfies Model<"openai-completions">,
- "mistralai/mistral-large-2512": {
- id: "mistralai/mistral-large-2512",
- name: "Mistral: Mistral Large 3 2512",
- api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- reasoning: false,
- input: ["text", "image"],
- cost: {
- input: 0.5,
- output: 1.5,
- cacheRead: 0.049999999999999996,
- cacheWrite: 0,
- },
- contextWindow: 262144,
- maxTokens: 209715,
- } satisfies Model<"openai-completions">,
"mistralai/mistral-medium-3": {
id: "mistralai/mistral-medium-3",
name: "Mistral: Mistral Medium 3",
@@ -12696,6 +13500,23 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 209715,
} satisfies Model<"openai-completions">,
+ "mistralai/mistral-small-3.1-24b-instruct": {
+ id: "mistralai/mistral-small-3.1-24b-instruct",
+ name: "Mistral: Mistral Small 3.1 24B",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: false,
+ input: ["text", "image"],
+ cost: {
+ input: 0.351,
+ output: 0.5549999999999999,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 128000,
+ maxTokens: 102400,
+ } satisfies Model<"openai-completions">,
"mistralai/mistral-small-3.2-24b-instruct": {
id: "mistralai/mistral-small-3.2-24b-instruct",
name: "Mistral: Mistral Small 3.2 24B",
@@ -12705,12 +13526,12 @@ export const MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
- input: 0.075,
- output: 0.19999999999999998,
+ input: 0.09375,
+ output: 0.25,
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 131072,
+ contextWindow: 256000,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"mistralai/mixtral-8x22b-instruct": {
@@ -12762,7 +13583,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 100352,
+ maxTokens: 98304,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2-0905": {
id: "moonshotai/kimi-k2-0905",
@@ -12779,7 +13600,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 100352,
+ maxTokens: 98304,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2-thinking": {
id: "moonshotai/kimi-k2-thinking",
@@ -12798,7 +13619,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 100352,
+ maxTokens: 98304,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2.5": {
id: "moonshotai/kimi-k2.5",
@@ -12849,8 +13670,8 @@ export const MODELS = {
thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.66,
- output: 3.4,
+ input: 0.7062,
+ output: 3.21,
cacheRead: 0.18,
cacheWrite: 0,
},
@@ -12875,39 +13696,37 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 1048576,
} satisfies Model<"openai-completions">,
- "nex-agi/nex-n2-mini": {
- id: "nex-agi/nex-n2-mini",
- name: "Nex AGI: Nex-N2-Mini",
+ "nex-agi/nex-n2.5-mini:free": {
+ id: "nex-agi/nex-n2.5-mini:free",
+ name: "Nex AGI: Nex-N2.5-Mini (free)",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
- compat: {"supportsReasoningEffort":false},
reasoning: true,
- thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
+ thinkingLevelMap: {"minimal":null,"low":null,"medium":"medium","high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.024999999999999998,
- output: 0.09999999999999999,
- cacheRead: 0.0025,
+ input: 0,
+ output: 0,
+ cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 235929,
} satisfies Model<"openai-completions">,
- "nex-agi/nex-n2-pro": {
- id: "nex-agi/nex-n2-pro",
- name: "Nex AGI: Nex-N2-Pro",
+ "nex-agi/nex-n2.5-pro:free": {
+ id: "nex-agi/nex-n2.5-pro:free",
+ name: "Nex AGI: Nex-N2.5-Pro (free)",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
- compat: {"supportsReasoningEffort":false},
reasoning: true,
- thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
+ thinkingLevelMap: {"minimal":null,"low":null,"medium":"medium","high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.25,
- output: 1,
- cacheRead: 0.024999999999999998,
+ input: 0,
+ output: 0,
+ cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -12924,9 +13743,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.049999999999999996,
- output: 0.19999999999999998,
- cacheRead: 0.03,
+ input: 0.06,
+ output: 0.24,
+ cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -12961,13 +13780,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":null,"xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.08499999999999999,
- output: 0.39999999999999997,
+ input: 0.08,
+ output: 0.44999999999999996,
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 1000000,
- maxTokens: 16384,
+ contextWindow: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-super-120b-a12b:free": {
id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -12997,13 +13816,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":"medium","high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.625,
- output: 3.125,
- cacheRead: 0.1875,
- cacheWrite: 0,
+ input: 0.6,
+ output: 2.4,
+ cacheRead: 0.12,
+ cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 32768,
+ maxTokens: 182520,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-ultra-550b-a55b:free": {
id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -13034,13 +13853,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.08,
+ input: 0.07,
output: 0.19999999999999998,
cacheRead: 0.04,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 131072,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3.5-lightning:free": {
id: "nvidia/nemotron-3.5-lightning:free",
@@ -13146,23 +13965,6 @@ export const MODELS = {
contextWindow: 128000,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
- "openai/gpt-4-turbo-preview": {
- id: "openai/gpt-4-turbo-preview",
- name: "OpenAI: GPT-4 Turbo Preview",
- api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- reasoning: false,
- input: ["text"],
- cost: {
- input: 10,
- output: 30,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 128000,
- maxTokens: 4096,
- } satisfies Model<"openai-completions">,
"openai/gpt-4.1": {
id: "openai/gpt-4.1",
name: "OpenAI: GPT-4.1",
@@ -13863,13 +14665,13 @@ export const MODELS = {
thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.037,
- output: 0.16999999999999998,
- cacheRead: 0,
+ input: 0.15,
+ output: 0.6,
+ cacheRead: 0.075,
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 117964,
+ maxTokens: 65536,
} satisfies Model<"openai-completions">,
"openai/gpt-oss-20b": {
id: "openai/gpt-oss-20b",
@@ -14166,6 +14968,24 @@ export const MODELS = {
contextWindow: 262144,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
+ "prism-ml/ternary-bonsai-2-27b": {
+ id: "prism-ml/ternary-bonsai-2-27b",
+ name: "PrismML: Ternary Bonsai 2 27B",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":null,"medium":"medium","high":null,"xhigh":"xhigh","max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 0.075,
+ output: 0.5,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 32768,
+ } satisfies Model<"openai-completions">,
"qwen/qwen-2.5-72b-instruct": {
id: "qwen/qwen-2.5-72b-instruct",
name: "Qwen2.5 72B Instruct",
@@ -14281,13 +15101,13 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 0.09,
- output: 0.55,
- cacheRead: 0,
+ input: 0.0875,
+ output: 0.35,
+ cacheRead: 0.0175,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 16384,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3-235b-a22b-thinking-2507": {
id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -14531,13 +15351,13 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 0.09999999999999999,
+ input: 0.09,
output: 1.1,
- cacheRead: 0.07,
+ cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 235929,
+ maxTokens: 16384,
} satisfies Model<"openai-completions">,
"qwen/qwen3-next-80b-a3b-thinking": {
id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -14603,13 +15423,13 @@ export const MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
- input: 0.15,
- output: 0.6,
+ input: 0.13,
+ output: 0.52,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 16384,
+ maxTokens: 32768,
} satisfies Model<"openai-completions">,
"qwen/qwen3-vl-30b-a3b-thinking": {
id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -14694,13 +15514,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.29,
- output: 2.4,
+ input: 0.26,
+ output: 2.08,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 81920,
+ maxTokens: 65536,
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-27b": {
id: "qwen/qwen3.5-27b",
@@ -14776,7 +15596,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 235929,
+ maxTokens: 32768,
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-flash-02-23": {
id: "qwen/qwen3.5-flash-02-23",
@@ -14865,8 +15685,8 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 0.09999999999999999,
- output: 0.8999999999999999,
+ input: 0.15,
+ output: 1,
cacheRead: 0.049999999999999996,
cacheWrite: 0,
},
@@ -15003,7 +15823,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 262144,
+ maxTokens: 131072,
} satisfies Model<"openai-completions">,
"qwen/qwen3.8-27b": {
id: "qwen/qwen3.8-27b",
@@ -15023,6 +15843,24 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
+ "qwen/qwen3.8-27b:free": {
+ id: "qwen/qwen3.8-27b:free",
+ name: "Qwen: Qwen3.8 27B (free)",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":null,"xhigh":"xhigh","max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 0,
+ output: 0,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 235929,
+ } satisfies Model<"openai-completions">,
"qwen/qwen3.8-flash": {
id: "qwen/qwen3.8-flash",
name: "Qwen: Qwen3.8 Flash",
@@ -15094,6 +15932,24 @@ export const MODELS = {
contextWindow: 256000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
+ "sakana/fugu-max": {
+ id: "sakana/fugu-max",
+ name: "Sakana: Fugu Max",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh","max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 2,
+ output: 6,
+ cacheRead: 0.25,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-completions">,
"sakana/fugu-ultra": {
id: "sakana/fugu-ultra",
name: "Sakana: Fugu Ultra",
@@ -15112,6 +15968,24 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
+ "sakana/fugu-ultra-v2": {
+ id: "sakana/fugu-ultra-v2",
+ name: "Sakana: Fugu Ultra v2",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh","max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 5,
+ output: 30,
+ cacheRead: 0.5,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-completions">,
"sakana/sakana-namazu": {
id: "sakana/sakana-namazu",
name: "Sakana: Sakana Namazu",
@@ -15238,23 +16112,6 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 64000,
} satisfies Model<"openai-completions">,
- "thedrummer/unslopnemo-12b": {
- id: "thedrummer/unslopnemo-12b",
- name: "TheDrummer: UnslopNemo 12B",
- api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- reasoning: false,
- input: ["text"],
- cost: {
- input: 0.39999999999999997,
- output: 0.39999999999999997,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 1024000,
- maxTokens: 819200,
- } satisfies Model<"openai-completions">,
"thinkingmachines/inkling": {
id: "thinkingmachines/inkling",
name: "Thinking Machines: Inkling",
@@ -15327,15 +16184,31 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 262144,
} satisfies Model<"openai-completions">,
+ "unbiased/pareto": {
+ id: "unbiased/pareto",
+ name: "Pareto",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: false,
+ input: ["text", "image"],
+ cost: {
+ input: 2.5,
+ output: 7.5,
+ cacheRead: 0.25,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 131072,
+ } satisfies Model<"openai-completions">,
"upstage/solar-pro-3": {
id: "upstage/solar-pro-3",
name: "Upstage: Solar Pro 3",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
- compat: {"supportsReasoningEffort":false},
reasoning: true,
- thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
+ thinkingLevelMap: {"minimal":"minimal","low":"low","medium":"medium","high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
input: 0.15,
@@ -15352,14 +16225,13 @@ export const MODELS = {
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
- compat: {"supportsReasoningEffort":false},
reasoning: true,
- thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
+ thinkingLevelMap: {"minimal":"minimal","low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},
input: ["text"],
cost: {
- input: 0.03,
- output: 0.12,
- cacheRead: 0.006,
+ input: 0.09,
+ output: 0.36,
+ cacheRead: 0.018,
cacheWrite: 0,
},
contextWindow: 524288,
@@ -15438,6 +16310,24 @@ export const MODELS = {
contextWindow: 500000,
maxTokens: 450000,
} satisfies Model<"openai-completions">,
+ "x-ai/grok-4.7": {
+ id: "x-ai/grok-4.7",
+ name: "SpaceXAI: Grok 4.7",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 1.5999999999999999,
+ output: 4.8,
+ cacheRead: 0.39999999999999997,
+ cacheWrite: 0,
+ },
+ contextWindow: 500000,
+ maxTokens: 450000,
+ } satisfies Model<"openai-completions">,
"x-ai/grok-build-0.1": {
id: "x-ai/grok-build-0.1",
name: "SpaceXAI: Grok Build 0.1",
@@ -15563,13 +16453,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.55,
- output: 2.2,
- cacheRead: 0.11,
+ input: 0.43,
+ output: 1.75,
+ cacheRead: 0.08,
cacheWrite: 0,
},
contextWindow: 204800,
- maxTokens: 131072,
+ maxTokens: 16384,
} satisfies Model<"openai-completions">,
"z-ai/glm-4.6v": {
id: "z-ai/glm-4.6v",
@@ -15620,13 +16510,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text"],
cost: {
- input: 0.06,
+ input: 0.060500000000000005,
output: 0.39999999999999997,
- cacheRead: 0.01,
+ cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 202752,
- maxTokens: 16384,
+ contextWindow: 200000,
+ maxTokens: 117964,
} satisfies Model<"openai-completions">,
"z-ai/glm-5": {
id: "z-ai/glm-5",
@@ -15695,32 +16585,14 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh","max":null},
input: ["text"],
cost: {
- input: 0.966,
- output: 3.036,
- cacheRead: 0.1932,
+ input: 0.6496,
+ output: 2.0416,
+ cacheRead: 0.12064,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
- "z-ai/glm-5.2:free": {
- id: "z-ai/glm-5.2:free",
- name: "Z.ai: GLM 5.2 (free)",
- api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- reasoning: true,
- thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh","max":null},
- input: ["text"],
- cost: {
- input: 0,
- output: 0,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 256000,
- maxTokens: 230400,
- } satisfies Model<"openai-completions">,
"z-ai/glm-5.3": {
id: "z-ai/glm-5.3",
name: "Z.ai: GLM 5.3",
@@ -15731,13 +16603,13 @@ export const MODELS = {
thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
input: ["text"],
cost: {
- input: 1.4,
- output: 4.4,
- cacheRead: 0.14,
+ input: 0.9099999999999999,
+ output: 2.8600000000000003,
+ cacheRead: 0.16899999999999998,
cacheWrite: 0,
},
contextWindow: 1310720,
- maxTokens: 262144,
+ maxTokens: 131072,
} satisfies Model<"openai-completions">,
"z-ai/glm-5.3-flash": {
id: "z-ai/glm-5.3-flash",
@@ -15751,10 +16623,28 @@ export const MODELS = {
cost: {
input: 0.075,
output: 0.25,
- cacheRead: 0.015,
+ cacheRead: 0.02,
cacheWrite: 0,
},
contextWindow: 1310720,
+ maxTokens: 102400,
+ } satisfies Model<"openai-completions">,
+ "z-ai/glm-5.3-flashx": {
+ id: "z-ai/glm-5.3-flashx",
+ name: "Z.ai: GLM 5.3 FlashX",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 0.37,
+ output: 1.25,
+ cacheRead: 0.075,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"z-ai/glm-5v-turbo": {
@@ -15796,7 +16686,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"~anthropic/claude-haiku-latest": {
id: "~anthropic/claude-haiku-latest",
- name: "Anthropic Claude Haiku Latest",
+ name: "Anthropic: Claude Haiku Latest",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
@@ -15833,7 +16723,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"~anthropic/claude-sonnet-latest": {
id: "~anthropic/claude-sonnet-latest",
- name: "Anthropic Claude Sonnet Latest",
+ name: "Anthropic: Claude Sonnet Latest",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
@@ -15849,9 +16739,45 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
+ "~deepseek/deepseek-flash-latest": {
+ id: "~deepseek/deepseek-flash-latest",
+ name: "DeepSeek: DeepSeek Flash Latest",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 0.12,
+ output: 0.48,
+ cacheRead: 0.0036,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
+ maxTokens: 943718,
+ } satisfies Model<"openai-completions">,
+ "~deepseek/deepseek-pro-latest": {
+ id: "~deepseek/deepseek-pro-latest",
+ name: "DeepSeek: DeepSeek Pro Latest",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
+ input: ["text"],
+ cost: {
+ input: 0.57024,
+ output: 1.7107199999999998,
+ cacheRead: 0.019008,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
+ maxTokens: 384000,
+ } satisfies Model<"openai-completions">,
"~deepseek/deepseek-v4-flash-latest": {
id: "~deepseek/deepseek-v4-flash-latest",
- name: "DeepSeek V4 Flash Latest",
+ name: "DeepSeek: DeepSeek V4 Flash Latest",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
@@ -15860,9 +16786,9 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
input: ["text"],
cost: {
- input: 0.045,
- output: 0.09,
- cacheRead: 0.009,
+ input: 0.04,
+ output: 0.16,
+ cacheRead: 0.016,
cacheWrite: 0,
},
contextWindow: 1310720,
@@ -15870,7 +16796,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"~google/gemini-flash-latest": {
id: "~google/gemini-flash-latest",
- name: "Google Gemini Flash Latest",
+ name: "Google: Gemini Flash Latest",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
@@ -15888,7 +16814,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"~google/gemini-pro-latest": {
id: "~google/gemini-pro-latest",
- name: "Google Gemini Pro Latest",
+ name: "Google: Gemini Pro Latest",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
@@ -15896,124 +16822,417 @@ export const MODELS = {
thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 2,
- output: 12,
- cacheRead: 0.19999999999999998,
- cacheWrite: 0.375,
+ input: 2,
+ output: 12,
+ cacheRead: 0.19999999999999998,
+ cacheWrite: 0.375,
+ },
+ contextWindow: 1048576,
+ maxTokens: 65536,
+ } satisfies Model<"openai-completions">,
+ "~moonshotai/kimi-latest": {
+ id: "~moonshotai/kimi-latest",
+ name: "MoonshotAI: Kimi Latest",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 1.7,
+ output: 8.5,
+ cacheRead: 0.16999999999999998,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
+ maxTokens: 943718,
+ } satisfies Model<"openai-completions">,
+ "~openai/gpt-astra-latest": {
+ id: "~openai/gpt-astra-latest",
+ name: "OpenAI: GPT Astra Latest",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 10,
+ output: 50,
+ cacheRead: 1,
+ cacheWrite: 12.5,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-completions">,
+ "~openai/gpt-luna-latest": {
+ id: "~openai/gpt-luna-latest",
+ name: "OpenAI: GPT Luna Latest",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 0.19999999999999998,
+ output: 1.2,
+ cacheRead: 0.02,
+ cacheWrite: 0.25,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-completions">,
+ "~openai/gpt-mini-latest": {
+ id: "~openai/gpt-mini-latest",
+ name: "OpenAI: GPT Mini Latest",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 0.75,
+ output: 4.5,
+ cacheRead: 0.075,
+ cacheWrite: 0,
+ },
+ contextWindow: 400000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-completions">,
+ "~openai/gpt-sol-latest": {
+ id: "~openai/gpt-sol-latest",
+ name: "OpenAI: GPT Sol Latest",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 2,
+ output: 10,
+ cacheRead: 0.19999999999999998,
+ cacheWrite: 2.5,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-completions">,
+ "~openai/gpt-terra-latest": {
+ id: "~openai/gpt-terra-latest",
+ name: "OpenAI: GPT Terra Latest",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 2,
+ output: 12,
+ cacheRead: 0.19999999999999998,
+ cacheWrite: 2.5,
+ },
+ contextWindow: 1050000,
+ maxTokens: 128000,
+ } satisfies Model<"openai-completions">,
+ "~x-ai/grok-latest": {
+ id: "~x-ai/grok-latest",
+ name: "xAI: Grok Latest",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 1.5999999999999999,
+ output: 4.8,
+ cacheRead: 0.39999999999999997,
+ cacheWrite: 0,
+ },
+ contextWindow: 500000,
+ maxTokens: 450000,
+ } satisfies Model<"openai-completions">,
+ "~z-ai/glm-flash-latest": {
+ id: "~z-ai/glm-flash-latest",
+ name: "Z.ai: GLM Flash Latest",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
+ input: ["text", "image"],
+ cost: {
+ input: 0.075,
+ output: 0.25,
+ cacheRead: 0.02,
+ cacheWrite: 0,
+ },
+ contextWindow: 1310720,
+ maxTokens: 102400,
+ } satisfies Model<"openai-completions">,
+ "~z-ai/glm-latest": {
+ id: "~z-ai/glm-latest",
+ name: "Z.ai: GLM Latest",
+ api: "openai-completions",
+ provider: "openrouter",
+ baseUrl: "https://openrouter.ai/api/v1",
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
+ input: ["text"],
+ cost: {
+ input: 0.7728,
+ output: 2.4288,
+ cacheRead: 0.14352,
+ cacheWrite: 0,
+ },
+ contextWindow: 1310720,
+ maxTokens: 131072,
+ } satisfies Model<"openai-completions">,
+ },
+ "prime-inference": {
+ "Qwen/Qwen3-235B-A22B-Instruct-2507": {
+ id: "Qwen/Qwen3-235B-A22B-Instruct-2507",
+ name: "Qwen3 235B A22B Instruct 2507",
+ api: "openai-completions",
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
+ reasoning: false,
+ input: ["text"],
+ cost: {
+ input: 0.25,
+ output: 1,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 235929,
+ } satisfies Model<"openai-completions">,
+ "Qwen/Qwen3-235B-A22B-Thinking-2507": {
+ id: "Qwen/Qwen3-235B-A22B-Thinking-2507",
+ name: "Qwen3 235B A22B Thinking 2507",
+ api: "openai-completions",
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"openrouter"},
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
+ input: ["text"],
+ cost: {
+ input: 0.3,
+ output: 3,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 131072,
+ maxTokens: 117964,
+ } satisfies Model<"openai-completions">,
+ "Qwen/Qwen3-30B-A3B-Thinking-2507": {
+ id: "Qwen/Qwen3-30B-A3B-Thinking-2507",
+ name: "Qwen3 30B A3B Thinking 2507",
+ api: "openai-completions",
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"openrouter"},
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
+ input: ["text"],
+ cost: {
+ input: 0.2,
+ output: 2.4,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 81920,
+ maxTokens: 32768,
+ } satisfies Model<"openai-completions">,
+ "Qwen/Qwen3-VL-30B-A3B-Thinking": {
+ id: "Qwen/Qwen3-VL-30B-A3B-Thinking",
+ name: "Qwen3 VL 30B A3B Thinking",
+ api: "openai-completions",
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"openrouter"},
+ reasoning: true,
+ thinkingLevelMap: {"off":null,"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 0.2,
+ output: 2.4,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 32768,
+ } satisfies Model<"openai-completions">,
+ "Qwen/Qwen3.5-0.8B": {
+ id: "Qwen/Qwen3.5-0.8B",
+ name: "QWEN3.5 0.8B",
+ api: "openai-completions",
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
+ reasoning: false,
+ input: ["text"],
+ cost: {
+ input: 0.04,
+ output: 0.08,
+ cacheRead: 0.036,
+ cacheWrite: 0.04,
+ },
+ contextWindow: 128000,
+ maxTokens: 8192,
+ } satisfies Model<"openai-completions">,
+ "Qwen/Qwen3.5-122B-A10B": {
+ id: "Qwen/Qwen3.5-122B-A10B",
+ name: "QWEN3.5 122B A10B",
+ api: "openai-completions",
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"openrouter"},
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 0.3,
+ output: 0.9,
+ cacheRead: 0.27,
+ cacheWrite: 0.3,
+ },
+ contextWindow: 262144,
+ maxTokens: 65536,
+ } satisfies Model<"openai-completions">,
+ "Qwen/Qwen3.5-2B": {
+ id: "Qwen/Qwen3.5-2B",
+ name: "QWEN3.5 2B",
+ api: "openai-completions",
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
+ reasoning: false,
+ input: ["text"],
+ cost: {
+ input: 0.06,
+ output: 0.18,
+ cacheRead: 0.054,
+ cacheWrite: 0.06,
},
- contextWindow: 1048576,
- maxTokens: 65536,
+ contextWindow: 128000,
+ maxTokens: 8192,
} satisfies Model<"openai-completions">,
- "~moonshotai/kimi-latest": {
- id: "~moonshotai/kimi-latest",
- name: "MoonshotAI Kimi Latest",
+ "Qwen/Qwen3.5-4B": {
+ id: "Qwen/Qwen3.5-4B",
+ name: "QWEN3.5 4B",
api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- reasoning: true,
- thinkingLevelMap: {"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
- input: ["text", "image"],
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
+ reasoning: false,
+ input: ["text"],
cost: {
- input: 2.5500000000000003,
- output: 12.75,
- cacheRead: 0.25599998999999996,
- cacheWrite: 0,
+ input: 0.1,
+ output: 0.3,
+ cacheRead: 0.09,
+ cacheWrite: 0.1,
},
- contextWindow: 1048576,
- maxTokens: 943718,
+ contextWindow: 128000,
+ maxTokens: 8192,
} satisfies Model<"openai-completions">,
- "~openai/gpt-latest": {
- id: "~openai/gpt-latest",
- name: "OpenAI GPT Latest",
+ "Qwen/Qwen3.5-9B": {
+ id: "Qwen/Qwen3.5-9B",
+ name: "QWEN3.5 9B",
api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"thinkingFormat":"openrouter"},
reasoning: true,
- thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},
+ thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},
input: ["text", "image"],
cost: {
- input: 2,
- output: 10,
- cacheRead: 0.19999999999999998,
- cacheWrite: 2.5,
+ input: 0.18,
+ output: 0.54,
+ cacheRead: 0.162,
+ cacheWrite: 0.18,
},
- contextWindow: 1050000,
- maxTokens: 128000,
+ contextWindow: 262144,
+ maxTokens: 32768,
} satisfies Model<"openai-completions">,
- "~openai/gpt-mini-latest": {
- id: "~openai/gpt-mini-latest",
- name: "OpenAI GPT Mini Latest",
+ "alibaba/qwen3.5-flash": {
+ id: "alibaba/qwen3.5-flash",
+ name: "QWEN3.5 Flash",
api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- reasoning: true,
- thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":null},
- input: ["text", "image"],
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
+ reasoning: false,
+ input: ["text"],
cost: {
- input: 0.75,
- output: 4.5,
- cacheRead: 0.075,
+ input: 0.15,
+ output: 0.6,
+ cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 400000,
- maxTokens: 128000,
+ contextWindow: 128000,
+ maxTokens: 8192,
} satisfies Model<"openai-completions">,
- "~x-ai/grok-latest": {
- id: "~x-ai/grok-latest",
- name: "xAI: Grok Latest",
+ "alibaba/qwen3.7-max": {
+ id: "alibaba/qwen3.7-max",
+ name: "QWEN3.7 MAX",
api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- reasoning: true,
- thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":null},
- input: ["text", "image"],
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
+ reasoning: false,
+ input: ["text"],
cost: {
- input: 2,
- output: 6,
- cacheRead: 0.5,
+ input: 3.75,
+ output: 11.25,
+ cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 500000,
- maxTokens: 450000,
+ contextWindow: 128000,
+ maxTokens: 8192,
} satisfies Model<"openai-completions">,
- "~z-ai/glm-flash-latest": {
- id: "~z-ai/glm-flash-latest",
- name: "Z.ai: GLM Flash Latest",
+ "alibaba/qwen3.7-plus": {
+ id: "alibaba/qwen3.7-plus",
+ name: "QWEN3.7 Plus",
api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- reasoning: true,
- thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
- input: ["text", "image"],
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
+ reasoning: false,
+ input: ["text"],
cost: {
- input: 0.075,
- output: 0.25,
- cacheRead: 0.015,
+ input: 0.6,
+ output: 2.4,
+ cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 1310720,
- maxTokens: 943718,
+ contextWindow: 128000,
+ maxTokens: 8192,
} satisfies Model<"openai-completions">,
- "~z-ai/glm-latest": {
- id: "~z-ai/glm-latest",
- name: "Z.ai: GLM Latest",
+ "alibaba/qwen3.8-flash": {
+ id: "alibaba/qwen3.8-flash",
+ name: "QWEN3.8 Flash",
api: "openai-completions",
- provider: "openrouter",
- baseUrl: "https://openrouter.ai/api/v1",
- reasoning: true,
- thinkingLevelMap: {"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
+ reasoning: false,
input: ["text"],
cost: {
- input: 1.17,
- output: 3.9600000000000004,
- cacheRead: 0.234,
+ input: 0.225,
+ output: 0.705,
+ cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 1310720,
- maxTokens: 235929,
+ contextWindow: 128000,
+ maxTokens: 8192,
} satisfies Model<"openai-completions">,
- },
- "prime-inference": {
"anthropic/claude-fable-5": {
id: "anthropic/claude-fable-5",
name: "Claude Fable 5",
@@ -16225,7 +17444,7 @@ export const MODELS = {
cacheRead: 0.30000000000000004,
cacheWrite: 3.75,
},
- contextWindow: 200000,
+ contextWindow: 1000000,
maxTokens: 64000,
featured: true,
} satisfies Model<"openai-completions">,
@@ -16269,45 +17488,9 @@ export const MODELS = {
maxTokens: 128000,
featured: true,
} satisfies Model<"openai-completions">,
- "deepseek/deepseek-chat": {
- id: "deepseek/deepseek-chat",
- name: "Deepseek Chat",
- api: "openai-completions",
- provider: "prime-inference",
- baseUrl: "https://api.pinference.ai/api/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: false,
- input: ["text"],
- cost: {
- input: 0.4,
- output: 1.3,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 163840,
- maxTokens: 16384,
- } satisfies Model<"openai-completions">,
- "deepseek/deepseek-chat-v3-0324": {
- id: "deepseek/deepseek-chat-v3-0324",
- name: "Deepseek Chat V3 0324",
- api: "openai-completions",
- provider: "prime-inference",
- baseUrl: "https://api.pinference.ai/api/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: false,
- input: ["text"],
- cost: {
- input: 0.27,
- output: 1.12,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 163840,
- maxTokens: 147456,
- } satisfies Model<"openai-completions">,
"deepseek/deepseek-chat-v3.1": {
id: "deepseek/deepseek-chat-v3.1",
- name: "Deepseek Chat V3.1",
+ name: "DeepSeek V3.1",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16322,11 +17505,11 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 163840,
- maxTokens: 144900,
+ maxTokens: 32768,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v3.1-terminus": {
id: "deepseek/deepseek-v3.1-terminus",
- name: "Deepseek V3.1 Terminus",
+ name: "DeepSeek V3.1 Terminus",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16345,7 +17528,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v3.2": {
id: "deepseek/deepseek-v3.2",
- name: "Deepseek V3.2",
+ name: "DeepSeek V3.2",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16365,7 +17548,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v3.2-exp": {
id: "deepseek/deepseek-v3.2-exp",
- name: "Deepseek V3.2 EXP",
+ name: "DeepSeek V3.2 Exp",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16384,7 +17567,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-flash": {
id: "deepseek/deepseek-v4-flash",
- name: "Deepseek V4 Flash",
+ name: "DeepSeek V4 Flash 0423",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16404,7 +17587,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-flash-0731": {
id: "deepseek/deepseek-v4-flash-0731",
- name: "Deepseek V4 Flash 0731",
+ name: "DeepSeek V4 Flash 0731",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16419,11 +17602,11 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1310720,
- maxTokens: 131072,
+ maxTokens: 943718,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-pro": {
id: "deepseek/deepseek-v4-pro",
- name: "Deepseek V4 PRO",
+ name: "DeepSeek V4 Pro 0423",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16441,6 +17624,25 @@ export const MODELS = {
maxTokens: 384000,
featured: true,
} satisfies Model<"openai-completions">,
+ "deepseek/deepseek-v4.1-flash": {
+ id: "deepseek/deepseek-v4.1-flash",
+ name: "DeepSeek V4.1 Flash",
+ api: "openai-completions",
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false,"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
+ reasoning: true,
+ thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max","max":null},
+ input: ["text", "image"],
+ cost: {
+ input: 0.3,
+ output: 1.2,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
+ maxTokens: 384000,
+ } satisfies Model<"openai-completions">,
"google/gemini-2.5-flash": {
id: "google/gemini-2.5-flash",
name: "Gemini 2.5 Flash",
@@ -16481,7 +17683,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"google/gemini-2.5-pro": {
id: "google/gemini-2.5-pro",
- name: "Gemini 2.5 PRO",
+ name: "Gemini 2.5 Pro",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16519,7 +17721,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"google/gemini-3.1-pro-preview": {
id: "google/gemini-3.1-pro-preview",
- name: "Gemini 3.1 PRO Preview",
+ name: "Gemini 3.1 Pro Preview",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16614,7 +17816,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"google/gemma-3-27b-it": {
id: "google/gemma-3-27b-it",
- name: "Gemma 3 27B IT",
+ name: "Gemma 3 27B",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16663,8 +17865,8 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 80000,
- maxTokens: 80000,
+ contextWindow: 131072,
+ maxTokens: 117964,
} satisfies Model<"openai-completions">,
"meta-llama/llama-3.3-70b-instruct": {
id: "meta-llama/llama-3.3-70b-instruct",
@@ -16700,11 +17902,11 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 115200,
+ maxTokens: 16384,
} satisfies Model<"openai-completions">,
"minimax/minimax-m2.5": {
id: "minimax/minimax-m2.5",
- name: "Minimax M2.5",
+ name: "MiniMax M2.5",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16723,7 +17925,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"minimax/minimax-m2.7": {
id: "minimax/minimax-m2.7",
- name: "Minimax M2.7",
+ name: "MiniMax M2.7",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16742,7 +17944,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"minimax/minimax-m3": {
id: "minimax/minimax-m3",
- name: "Minimax M3",
+ name: "MiniMax M3",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16756,7 +17958,7 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 524288,
+ contextWindow: 1048576,
maxTokens: 512000,
featured: true,
} satisfies Model<"openai-completions">,
@@ -16768,15 +17970,15 @@ export const MODELS = {
baseUrl: "https://api.pinference.ai/api/v1",
compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
reasoning: false,
- input: ["text", "image"],
+ input: ["text"],
cost: {
input: 0.5,
output: 1.5,
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 262144,
- maxTokens: 209715,
+ contextWindow: 128000,
+ maxTokens: 8192,
} satisfies Model<"openai-completions">,
"mistralai/mistral-nemo": {
id: "mistralai/mistral-nemo",
@@ -16798,7 +18000,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"mistralai/mistral-small-2603": {
id: "mistralai/mistral-small-2603",
- name: "Mistral Small 2603",
+ name: "Mistral Small 4",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16817,7 +18019,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"mistralai/mixtral-8x22b-instruct": {
id: "mistralai/mixtral-8x22b-instruct",
- name: "Mixtral 8X22B Instruct",
+ name: "Mixtral 8x22B Instruct",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16848,7 +18050,7 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 98304,
+ contextWindow: 262144,
maxTokens: 98304,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2.5": {
@@ -16868,7 +18070,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 65535,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2.6": {
id: "moonshotai/kimi-k2.6",
@@ -16887,7 +18089,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 262144,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2.7-code": {
id: "moonshotai/kimi-k2.7-code",
@@ -16926,7 +18128,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1048576,
- maxTokens: 1048576,
+ maxTokens: 943718,
featured: true,
} satisfies Model<"openai-completions">,
"nvidia/nemotron-3-nano-30b-a3b": {
@@ -16949,29 +18151,9 @@ export const MODELS = {
maxTokens: 235929,
featured: true,
} satisfies Model<"openai-completions">,
- "nvidia/nemotron-3-super-120b-a12b": {
- id: "nvidia/nemotron-3-super-120b-a12b",
- name: "Nemotron 3 Super 120B A12B",
- api: "openai-completions",
- provider: "prime-inference",
- baseUrl: "https://api.pinference.ai/api/v1",
- compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
- reasoning: true,
- thinkingLevelMap: {"minimal":null,"low":"low","medium":"medium","high":null,"xhigh":null,"max":null},
- input: ["text"],
- cost: {
- input: 0.3,
- output: 0.65,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 262144,
- maxTokens: 4096,
- featured: true,
- } satisfies Model<"openai-completions">,
"openai/gpt-4.1": {
id: "openai/gpt-4.1",
- name: "GPT 4.1",
+ name: "GPT-4.1",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -16989,7 +18171,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-4.1-mini": {
id: "openai/gpt-4.1-mini",
- name: "GPT 4.1 Mini",
+ name: "GPT-4.1 Mini",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17007,7 +18189,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-4.1-nano": {
id: "openai/gpt-4.1-nano",
- name: "GPT 4.1 Nano",
+ name: "GPT-4.1 Nano",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17025,7 +18207,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-4o": {
id: "openai/gpt-4o",
- name: "GPT 4O",
+ name: "GPT-4o",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17043,7 +18225,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-4o-mini": {
id: "openai/gpt-4o-mini",
- name: "GPT 4O Mini",
+ name: "GPT-4o-mini",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17061,7 +18243,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5": {
id: "openai/gpt-5",
- name: "GPT 5",
+ name: "GPT-5",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17080,7 +18262,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5-mini": {
id: "openai/gpt-5-mini",
- name: "GPT 5 Mini",
+ name: "GPT-5 Mini",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17099,7 +18281,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5-nano": {
id: "openai/gpt-5-nano",
- name: "GPT 5 Nano",
+ name: "GPT-5 Nano",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17118,7 +18300,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5.1": {
id: "openai/gpt-5.1",
- name: "GPT 5.1",
+ name: "GPT-5.1",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17137,7 +18319,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5.2": {
id: "openai/gpt-5.2",
- name: "GPT 5.2",
+ name: "GPT-5.2",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17156,7 +18338,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5.2-pro": {
id: "openai/gpt-5.2-pro",
- name: "GPT 5.2 PRO",
+ name: "GPT-5.2 Pro",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17175,7 +18357,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5.3-codex": {
id: "openai/gpt-5.3-codex",
- name: "GPT 5.3 Codex",
+ name: "GPT-5.3-Codex",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17195,7 +18377,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5.4": {
id: "openai/gpt-5.4",
- name: "GPT 5.4",
+ name: "GPT-5.4",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17215,7 +18397,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5.4-mini": {
id: "openai/gpt-5.4-mini",
- name: "GPT 5.4 Mini",
+ name: "GPT-5.4 Mini",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17235,7 +18417,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5.4-nano": {
id: "openai/gpt-5.4-nano",
- name: "GPT 5.4 Nano",
+ name: "GPT-5.4 Nano",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17254,7 +18436,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5.4-pro": {
id: "openai/gpt-5.4-pro",
- name: "GPT 5.4 PRO",
+ name: "GPT-5.4 Pro",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17274,7 +18456,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5.5": {
id: "openai/gpt-5.5",
- name: "GPT 5.5",
+ name: "GPT-5.5",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17313,7 +18495,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5.6-luna": {
id: "openai/gpt-5.6-luna",
- name: "GPT 5.6 Luna",
+ name: "GPT-5.6 Luna",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17332,7 +18514,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5.6-luna-pro": {
id: "openai/gpt-5.6-luna-pro",
- name: "GPT 5.6 Luna PRO",
+ name: "GPT-5.6 Luna Pro",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17351,7 +18533,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5.6-sol": {
id: "openai/gpt-5.6-sol",
- name: "GPT 5.6 SOL",
+ name: "GPT-5.6 Sol",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17370,7 +18552,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5.6-sol-pro": {
id: "openai/gpt-5.6-sol-pro",
- name: "GPT 5.6 SOL PRO",
+ name: "GPT-5.6 Sol Pro",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17389,7 +18571,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5.6-terra": {
id: "openai/gpt-5.6-terra",
- name: "GPT 5.6 Terra",
+ name: "GPT-5.6 Terra",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17408,7 +18590,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-5.6-terra-pro": {
id: "openai/gpt-5.6-terra-pro",
- name: "GPT 5.6 Terra PRO",
+ name: "GPT-5.6 Terra Pro",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17427,7 +18609,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-6-astra": {
id: "openai/gpt-6-astra",
- name: "GPT 6 Astra",
+ name: "GPT-6 Astra",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17446,7 +18628,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"openai/gpt-oss-120b": {
id: "openai/gpt-oss-120b",
- name: "GPT OSS 120B",
+ name: "gpt-oss-120b",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17461,11 +18643,11 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 117964,
+ maxTokens: 65536,
} satisfies Model<"openai-completions">,
"openai/gpt-oss-20b": {
id: "openai/gpt-oss-20b",
- name: "GPT OSS 20B",
+ name: "gpt-oss-20b",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17480,7 +18662,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 131072,
- maxTokens: 131072,
+ maxTokens: 117964,
} satisfies Model<"openai-completions">,
"poolside/laguna-s-2.1": {
id: "poolside/laguna-s-2.1",
@@ -17522,7 +18704,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"qwen/qwen3-235b-a22b-2507": {
id: "qwen/qwen3-235b-a22b-2507",
- name: "QWEN3 235B A22B 2507",
+ name: "Qwen3 235B A22B Instruct 2507",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17536,11 +18718,11 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 16384,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3-30b-a3b-instruct-2507": {
id: "qwen/qwen3-30b-a3b-instruct-2507",
- name: "QWEN3 30B A3B Instruct 2507",
+ name: "Qwen3 30B A3B Instruct 2507",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17559,7 +18741,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"qwen/qwen3-8b": {
id: "qwen/qwen3-8b",
- name: "QWEN3 8B",
+ name: "Qwen3 8B",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17578,7 +18760,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"qwen/qwen3-coder": {
id: "qwen/qwen3-coder",
- name: "QWEN3 Coder",
+ name: "Qwen3 Coder 480B A35B",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17596,7 +18778,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"qwen/qwen3-coder-next": {
id: "qwen/qwen3-coder-next",
- name: "QWEN3 Coder Next",
+ name: "Qwen3 Coder Next",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17615,7 +18797,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"qwen/qwen3-max": {
id: "qwen/qwen3-max",
- name: "QWEN3 MAX",
+ name: "Qwen3 Max",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17634,7 +18816,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"qwen/qwen3-vl-235b-a22b-instruct": {
id: "qwen/qwen3-vl-235b-a22b-instruct",
- name: "QWEN3 VL 235B A22B Instruct",
+ name: "Qwen3 VL 235B A22B Instruct",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17652,7 +18834,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"qwen/qwen3-vl-235b-a22b-thinking": {
id: "qwen/qwen3-vl-235b-a22b-thinking",
- name: "QWEN3 VL 235B A22B Thinking",
+ name: "Qwen3 VL 235B A22B Thinking",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17672,7 +18854,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"qwen/qwen3-vl-30b-a3b-instruct": {
id: "qwen/qwen3-vl-30b-a3b-instruct",
- name: "QWEN3 VL 30B A3B Instruct",
+ name: "Qwen3 VL 30B A3B Instruct",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17686,11 +18868,11 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 16384,
+ maxTokens: 32768,
} satisfies Model<"openai-completions">,
"qwen/qwen3-vl-8b-instruct": {
id: "qwen/qwen3-vl-8b-instruct",
- name: "QWEN3 VL 8B Instruct",
+ name: "Qwen3 VL 8B Instruct",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17708,7 +18890,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-35b-a3b": {
id: "qwen/qwen3.5-35b-a3b",
- name: "QWEN3.5 35B A3B",
+ name: "Qwen3.5-35B-A3B",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17727,7 +18909,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-397b-a17b": {
id: "qwen/qwen3.5-397b-a17b",
- name: "QWEN3.5 397B A17B",
+ name: "Qwen3.5 397B A17B",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17742,11 +18924,11 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
- maxTokens: 65536,
+ maxTokens: 235929,
} satisfies Model<"openai-completions">,
"qwen/qwen3.6-27b": {
id: "qwen/qwen3.6-27b",
- name: "QWEN3.6 27B",
+ name: "Qwen3.6 27B",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17765,7 +18947,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"qwen/qwen3.6-35b-a3b": {
id: "qwen/qwen3.6-35b-a3b",
- name: "QWEN3.6 35B A3B",
+ name: "Qwen3.6 35B A3B",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17784,7 +18966,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"qwen/qwen3.7-flash": {
id: "qwen/qwen3.7-flash",
- name: "QWEN3.7 Flash",
+ name: "Qwen3.7 Flash",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17838,12 +19020,12 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 2000000,
- maxTokens: 30000,
+ maxTokens: 1800000,
featured: true,
} satisfies Model<"openai-completions">,
"x-ai/grok-4.20-multi-agent": {
id: "x-ai/grok-4.20-multi-agent",
- name: "Grok 4.20 Multi Agent",
+ name: "Grok 4.20 Multi-Agent",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17858,7 +19040,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 2000000,
- maxTokens: 30000,
+ maxTokens: 1800000,
featured: true,
} satisfies Model<"openai-completions">,
"x-ai/grok-4.6": {
@@ -17882,7 +19064,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"xiaomi/mimo-v2.5": {
id: "xiaomi/mimo-v2.5",
- name: "Mimo V2.5",
+ name: "MiMo-V2.5",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17901,7 +19083,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"xiaomi/mimo-v2.5-pro": {
id: "xiaomi/mimo-v2.5-pro",
- name: "Mimo V2.5 PRO",
+ name: "MiMo-V2.5-Pro",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17939,7 +19121,7 @@ export const MODELS = {
} satisfies Model<"openai-completions">,
"z-ai/glm-4.5-air": {
id: "z-ai/glm-4.5-air",
- name: "GLM 4.5 AIR",
+ name: "GLM 4.5 Air",
api: "openai-completions",
provider: "prime-inference",
baseUrl: "https://api.pinference.ai/api/v1",
@@ -17973,7 +19155,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 204800,
- maxTokens: 131072,
+ maxTokens: 16384,
} satisfies Model<"openai-completions">,
"z-ai/glm-4.7": {
id: "z-ai/glm-4.7",
@@ -18010,8 +19192,8 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 202752,
- maxTokens: 16384,
+ contextWindow: 200000,
+ maxTokens: 117964,
} satisfies Model<"openai-completions">,
"z-ai/glm-5": {
id: "z-ai/glm-5",
@@ -18030,7 +19212,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 204800,
- maxTokens: 131072,
+ maxTokens: 128000,
featured: true,
} satisfies Model<"openai-completions">,
"z-ai/glm-5.1": {
@@ -18086,11 +19268,11 @@ export const MODELS = {
cost: {
input: 1.4,
output: 4.4,
- cacheRead: 0,
- cacheWrite: 0,
+ cacheRead: 1.26,
+ cacheWrite: 1.4,
},
- contextWindow: 1310720,
- maxTokens: 262144,
+ contextWindow: 1048576,
+ maxTokens: 131072,
} satisfies Model<"openai-completions">,
"z-ai/glm-5.3-flash": {
id: "z-ai/glm-5.3-flash",
@@ -18109,6 +19291,24 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 1310720,
+ maxTokens: 102400,
+ } satisfies Model<"openai-completions">,
+ "zai-org/GLM-4.7": {
+ id: "zai-org/GLM-4.7",
+ name: "GLM 4.7",
+ api: "openai-completions",
+ provider: "prime-inference",
+ baseUrl: "https://api.pinference.ai/api/v1",
+ compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"maxTokensField":"max_tokens","supportsStrictMode":false},
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0.6,
+ output: 2.2,
+ cacheRead: 0,
+ cacheWrite: 0,
+ },
+ contextWindow: 204800,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
},
@@ -18192,7 +19392,7 @@ export const MODELS = {
cost: {
input: 1.3,
output: 7.8,
- cacheRead: 0.26,
+ cacheRead: 0.13,
cacheWrite: 1.625,
},
contextWindow: 240000,
@@ -18348,8 +19548,8 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 131072,
- maxTokens: 32768,
+ contextWindow: 262114,
+ maxTokens: 262114,
} satisfies Model<"anthropic-messages">,
"alibaba/qwen3-next-80b-a3b-thinking": {
id: "alibaba/qwen3-next-80b-a3b-thinking",
@@ -18365,8 +19565,8 @@ export const MODELS = {
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 131072,
- maxTokens: 32768,
+ contextWindow: 262144,
+ maxTokens: 262144,
} satisfies Model<"anthropic-messages">,
"alibaba/qwen3-vl-235b-a22b-instruct": {
id: "alibaba/qwen3-vl-235b-a22b-instruct",
@@ -18430,7 +19630,7 @@ export const MODELS = {
cost: {
input: 0.09999999999999999,
output: 0.39999999999999997,
- cacheRead: 0.001,
+ cacheRead: 0.01,
cacheWrite: 0.125,
},
contextWindow: 1000000,
@@ -18446,7 +19646,7 @@ export const MODELS = {
input: ["text", "image"],
cost: {
input: 0.39999999999999997,
- output: 2.4,
+ output: 2.5,
cacheRead: 0.04,
cacheWrite: 0.5,
},
@@ -18481,7 +19681,7 @@ export const MODELS = {
cost: {
input: 0.5,
output: 3,
- cacheRead: 0.09999999999999999,
+ cacheRead: 0.049999999999999996,
cacheWrite: 0.625,
},
contextWindow: 1000000,
@@ -18581,7 +19781,7 @@ export const MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
- input: 0.16,
+ input: 0.15,
output: 0.47,
cacheRead: 0.016,
cacheWrite: 0.19999999999999998,
@@ -18589,23 +19789,6 @@ export const MODELS = {
contextWindow: 991000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
- "alibaba/qwen3.8-flash-next": {
- id: "alibaba/qwen3.8-flash-next",
- name: "Qwen 3.8 Flash Next",
- api: "anthropic-messages",
- provider: "vercel-ai-gateway",
- baseUrl: "https://ai-gateway.vercel.sh",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 0.12,
- output: 0.39999999999999997,
- cacheRead: 0.01,
- cacheWrite: 0,
- },
- contextWindow: 1048576,
- maxTokens: 1048576,
- } satisfies Model<"anthropic-messages">,
"alibaba/qwen3.8-max": {
id: "alibaba/qwen3.8-max",
name: "Qwen 3.8 Max",
@@ -18618,9 +19801,9 @@ export const MODELS = {
input: 2,
output: 6,
cacheRead: 0.25,
- cacheWrite: 2.5,
+ cacheWrite: 0,
},
- contextWindow: 1000000,
+ contextWindow: 262144,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"alibaba/qwen3.8-max-0902": {
@@ -18640,6 +19823,23 @@ export const MODELS = {
contextWindow: 991000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
+ "alibaba/qwen3.8-omni-flash": {
+ id: "alibaba/qwen3.8-omni-flash",
+ name: "Qwen 3.8 Omni Flash",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.15,
+ output: 0.47,
+ cacheRead: 0.016,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 131072,
+ } satisfies Model<"anthropic-messages">,
"amazon/nova-2-lite": {
id: "amazon/nova-2-lite",
name: "Nova 2 Lite",
@@ -19041,6 +20241,23 @@ export const MODELS = {
contextWindow: 256000,
maxTokens: 64000,
} satisfies Model<"anthropic-messages">,
+ "bytedance/seed-2.1-turbo": {
+ id: "bytedance/seed-2.1-turbo",
+ name: "Seed 2.1 Turbo",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.5,
+ output: 2.5,
+ cacheRead: 0.09999999999999999,
+ cacheWrite: 0,
+ },
+ contextWindow: 262144,
+ maxTokens: 262144,
+ } satisfies Model<"anthropic-messages">,
"cohere/command-a": {
id: "cohere/command-a",
name: "Command A",
@@ -19118,9 +20335,9 @@ export const MODELS = {
reasoning: false,
input: ["text"],
cost: {
- input: 0.28,
- output: 0.42,
- cacheRead: 0.028,
+ input: 0.62,
+ output: 1.85,
+ cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 128000,
@@ -19228,6 +20445,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 384000,
} satisfies Model<"anthropic-messages">,
+ "deepseek/deepseek-v4.1-flash": {
+ id: "deepseek/deepseek-v4.1-flash",
+ name: "DeepSeek V4.1 Flash",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 0.3,
+ output: 1.2,
+ cacheRead: 0.03,
+ cacheWrite: 0,
+ },
+ contextWindow: 1048576,
+ maxTokens: 32768,
+ } satisfies Model<"anthropic-messages">,
"google/gemini-2.5-flash": {
id: "google/gemini-2.5-flash",
name: "Gemini 2.5 Flash",
@@ -19466,6 +20700,23 @@ export const MODELS = {
contextWindow: 128000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
+ "inception/mercury-2.5": {
+ id: "inception/mercury-2.5",
+ name: "Mercury 2.5",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0.04,
+ output: 0.15,
+ cacheRead: 0.004,
+ cacheWrite: 0,
+ },
+ contextWindow: 260000,
+ maxTokens: 65536,
+ } satisfies Model<"anthropic-messages">,
"inception/mercury-coder-small": {
id: "inception/mercury-coder-small",
name: "Mercury Coder Small Beta",
@@ -19492,9 +20743,9 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
- input: 0.06,
- output: 0.18,
- cacheRead: 0.012,
+ input: 0.020999999999999998,
+ output: 0.063,
+ cacheRead: 0.004200000000000001,
cacheWrite: 0,
},
contextWindow: 256000,
@@ -19568,90 +20819,56 @@ export const MODELS = {
contextWindow: 256000,
maxTokens: 32000,
} satisfies Model<"anthropic-messages">,
- "interfaze/interfaze-beta": {
- id: "interfaze/interfaze-beta",
- name: "Interfaze Beta",
+ "inclusionai/ling-3.0-flash-vl": {
+ id: "inclusionai/ling-3.0-flash-vl",
+ name: "Ling 3.0 Flash VL",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text", "image"],
cost: {
- input: 1.5,
- output: 3.5,
+ input: 0,
+ output: 0,
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 1000000,
+ contextWindow: 256000,
maxTokens: 32000,
} satisfies Model<"anthropic-messages">,
- "kwaipilot/kat-coder-air-v2.5": {
- id: "kwaipilot/kat-coder-air-v2.5",
- name: "Kat Coder Air V2.5",
+ "inclusionai/ling-3.0-flash-vl-free": {
+ id: "inclusionai/ling-3.0-flash-vl-free",
+ name: "Ling 3.0 Flash VL (Free)",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text", "image"],
cost: {
- input: 0.15,
- output: 0.6,
- cacheRead: 0.03,
- cacheWrite: 0,
- },
- contextWindow: 256000,
- maxTokens: 80000,
- } satisfies Model<"anthropic-messages">,
- "kwaipilot/kat-coder-pro-v1": {
- id: "kwaipilot/kat-coder-pro-v1",
- name: "KAT-Coder-Pro V1",
- api: "anthropic-messages",
- provider: "vercel-ai-gateway",
- baseUrl: "https://ai-gateway.vercel.sh",
- reasoning: false,
- input: ["text"],
- cost: {
- input: 0.3,
- output: 1.2,
- cacheRead: 0.06,
+ input: 0,
+ output: 0,
+ cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 32000,
} satisfies Model<"anthropic-messages">,
- "kwaipilot/kat-coder-pro-v2": {
- id: "kwaipilot/kat-coder-pro-v2",
- name: "Kat Coder Pro V2",
- api: "anthropic-messages",
- provider: "vercel-ai-gateway",
- baseUrl: "https://ai-gateway.vercel.sh",
- reasoning: true,
- input: ["text"],
- cost: {
- input: 0.3,
- output: 1.2,
- cacheRead: 0.06,
- cacheWrite: 0,
- },
- contextWindow: 256000,
- maxTokens: 256000,
- } satisfies Model<"anthropic-messages">,
- "kwaipilot/kat-coder-pro-v2.5": {
- id: "kwaipilot/kat-coder-pro-v2.5",
- name: "Kat Coder Pro V2.5",
+ "interfaze/interfaze-beta": {
+ id: "interfaze/interfaze-beta",
+ name: "Interfaze Beta",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text", "image"],
cost: {
- input: 0.74,
- output: 2.96,
- cacheRead: 0.15,
+ input: 1.5,
+ output: 3.5,
+ cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 256000,
- maxTokens: 80000,
+ contextWindow: 1000000,
+ maxTokens: 32000,
} satisfies Model<"anthropic-messages">,
"meta/llama-3.1-70b": {
id: "meta/llama-3.1-70b",
@@ -19931,33 +21148,16 @@ export const MODELS = {
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
- reasoning: true,
- input: ["text"],
- cost: {
- input: 0.3,
- output: 1.2,
- cacheRead: 0.06,
- cacheWrite: 0.375,
- },
- contextWindow: 204800,
- maxTokens: 131000,
- } satisfies Model<"anthropic-messages">,
- "minimax/minimax-m2.7-free": {
- id: "minimax/minimax-m2.7-free",
- name: "MiniMax M2.7 (Free)",
- api: "anthropic-messages",
- provider: "vercel-ai-gateway",
- baseUrl: "https://ai-gateway.vercel.sh",
- reasoning: true,
- input: ["text"],
- cost: {
- input: 0,
- output: 0,
- cacheRead: 0,
- cacheWrite: 0,
+ reasoning: true,
+ input: ["text"],
+ cost: {
+ input: 0.3,
+ output: 1.2,
+ cacheRead: 0.06,
+ cacheWrite: 0.375,
},
- contextWindow: 196608,
- maxTokens: 196608,
+ contextWindow: 204800,
+ maxTokens: 131000,
} satisfies Model<"anthropic-messages">,
"minimax/minimax-m2.7-highspeed": {
id: "minimax/minimax-m2.7-highspeed",
@@ -19993,23 +21193,6 @@ export const MODELS = {
contextWindow: 512000,
maxTokens: 512000,
} satisfies Model<"anthropic-messages">,
- "minimax/minimax-m3-free": {
- id: "minimax/minimax-m3-free",
- name: "MiniMax M3 (Free)",
- api: "anthropic-messages",
- provider: "vercel-ai-gateway",
- baseUrl: "https://ai-gateway.vercel.sh",
- reasoning: true,
- input: ["text", "image"],
- cost: {
- input: 0,
- output: 0,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 1048576,
- maxTokens: 1048576,
- } satisfies Model<"anthropic-messages">,
"mistral/codestral": {
id: "mistral/codestral",
name: "Mistral Codestral",
@@ -20021,46 +21204,12 @@ export const MODELS = {
cost: {
input: 0.3,
output: 0.8999999999999999,
- cacheRead: 0,
+ cacheRead: 0.03,
cacheWrite: 0,
},
contextWindow: 128000,
maxTokens: 4000,
} satisfies Model<"anthropic-messages">,
- "mistral/devstral-2": {
- id: "mistral/devstral-2",
- name: "Devstral 2",
- api: "anthropic-messages",
- provider: "vercel-ai-gateway",
- baseUrl: "https://ai-gateway.vercel.sh",
- reasoning: false,
- input: ["text"],
- cost: {
- input: 0.39999999999999997,
- output: 2,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 256000,
- maxTokens: 256000,
- } satisfies Model<"anthropic-messages">,
- "mistral/devstral-small-2": {
- id: "mistral/devstral-small-2",
- name: "Devstral Small 2",
- api: "anthropic-messages",
- provider: "vercel-ai-gateway",
- baseUrl: "https://ai-gateway.vercel.sh",
- reasoning: false,
- input: ["text", "image"],
- cost: {
- input: 0.09999999999999999,
- output: 0.3,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 256000,
- maxTokens: 256000,
- } satisfies Model<"anthropic-messages">,
"mistral/ministral-14b": {
id: "mistral/ministral-14b",
name: "Ministral 14B",
@@ -20072,10 +21221,10 @@ export const MODELS = {
cost: {
input: 0.19999999999999998,
output: 0.19999999999999998,
- cacheRead: 0,
+ cacheRead: 0.02,
cacheWrite: 0,
},
- contextWindow: 256000,
+ contextWindow: 262144,
maxTokens: 256000,
} satisfies Model<"anthropic-messages">,
"mistral/ministral-3b": {
@@ -20089,10 +21238,10 @@ export const MODELS = {
cost: {
input: 0.09999999999999999,
output: 0.09999999999999999,
- cacheRead: 0,
+ cacheRead: 0.01,
cacheWrite: 0,
},
- contextWindow: 128000,
+ contextWindow: 131072,
maxTokens: 4000,
} satisfies Model<"anthropic-messages">,
"mistral/ministral-8b": {
@@ -20106,10 +21255,10 @@ export const MODELS = {
cost: {
input: 0.15,
output: 0.15,
- cacheRead: 0,
+ cacheRead: 0.015,
cacheWrite: 0,
},
- contextWindow: 128000,
+ contextWindow: 262144,
maxTokens: 4000,
} satisfies Model<"anthropic-messages">,
"mistral/mistral-large-3": {
@@ -20123,29 +21272,12 @@ export const MODELS = {
cost: {
input: 0.5,
output: 1.5,
- cacheRead: 0,
+ cacheRead: 0.049999999999999996,
cacheWrite: 0,
},
- contextWindow: 256000,
+ contextWindow: 262144,
maxTokens: 256000,
} satisfies Model<"anthropic-messages">,
- "mistral/mistral-medium": {
- id: "mistral/mistral-medium",
- name: "Mistral Medium 3.1",
- api: "anthropic-messages",
- provider: "vercel-ai-gateway",
- baseUrl: "https://ai-gateway.vercel.sh",
- reasoning: false,
- input: ["text", "image"],
- cost: {
- input: 0.39999999999999997,
- output: 2,
- cacheRead: 0,
- cacheWrite: 0,
- },
- contextWindow: 128000,
- maxTokens: 64000,
- } satisfies Model<"anthropic-messages">,
"mistral/mistral-medium-3.5": {
id: "mistral/mistral-medium-3.5",
name: "Mistral Medium Latest",
@@ -20157,10 +21289,10 @@ export const MODELS = {
cost: {
input: 1.5,
output: 7.5,
- cacheRead: 0,
+ cacheRead: 0.15,
cacheWrite: 0,
},
- contextWindow: 256000,
+ contextWindow: 262144,
maxTokens: 256000,
} satisfies Model<"anthropic-messages">,
"mistral/mistral-nemo": {
@@ -20170,15 +21302,15 @@ export const MODELS = {
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: false,
- input: ["text", "image"],
+ input: ["text"],
cost: {
- input: 0.15,
- output: 0.15,
+ input: 0.04,
+ output: 0.16999999999999998,
cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 128000,
- maxTokens: 128000,
+ contextWindow: 60288,
+ maxTokens: 16000,
} satisfies Model<"anthropic-messages">,
"mistral/mistral-small": {
id: "mistral/mistral-small",
@@ -20189,29 +21321,29 @@ export const MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
- input: 0.09999999999999999,
- output: 0.3,
- cacheRead: 0,
+ input: 0.15,
+ output: 0.6,
+ cacheRead: 0.015,
cacheWrite: 0,
},
- contextWindow: 32000,
+ contextWindow: 262144,
maxTokens: 4000,
} satisfies Model<"anthropic-messages">,
- "mistral/pixtral-12b": {
- id: "mistral/pixtral-12b",
- name: "Pixtral 12B 2409",
+ "mixedbread/toast-1": {
+ id: "mixedbread/toast-1",
+ name: "Toast 1",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: false,
- input: ["text", "image"],
+ input: ["text"],
cost: {
- input: 0.15,
- output: 0.15,
- cacheRead: 0,
+ input: 0.3,
+ output: 0.72,
+ cacheRead: 0.036,
cacheWrite: 0,
},
- contextWindow: 128000,
+ contextWindow: 131000,
maxTokens: 4000,
} satisfies Model<"anthropic-messages">,
"moonshotai/kimi-k2": {
@@ -20259,11 +21391,11 @@ export const MODELS = {
cost: {
input: 0.6,
output: 3,
- cacheRead: 0.09999999999999999,
+ cacheRead: 0,
cacheWrite: 0,
},
- contextWindow: 262114,
- maxTokens: 262114,
+ contextWindow: 256000,
+ maxTokens: 256000,
} satisfies Model<"anthropic-messages">,
"moonshotai/kimi-k2.6": {
id: "moonshotai/kimi-k2.6",
@@ -20362,8 +21494,8 @@ export const MODELS = {
input: ["text"],
cost: {
input: 0.049999999999999996,
- output: 0.24,
- cacheRead: 0,
+ output: 0.19999999999999998,
+ cacheRead: 0.024999999999999998,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -21178,10 +22310,10 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 2,
- output: 10,
- cacheRead: 0.19999999999999998,
- cacheWrite: 2.5,
+ input: 4,
+ output: 20,
+ cacheRead: 0.39999999999999997,
+ cacheWrite: 5,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -21196,10 +22328,10 @@ export const MODELS = {
thinkingLevelMap: {"xhigh":"xhigh","minimal":null,"max":"max"},
input: ["text", "image"],
cost: {
- input: 4,
- output: 20,
- cacheRead: 0.39999999999999997,
- cacheWrite: 5,
+ input: 8,
+ output: 40,
+ cacheRead: 0.7999999999999999,
+ cacheWrite: 10,
},
contextWindow: 1050000,
maxTokens: 128000,
@@ -21302,8 +22434,8 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
- input: 0.049999999999999996,
- output: 0.19999999999999998,
+ input: 0.03,
+ output: 0.14,
cacheRead: 0,
cacheWrite: 0,
},
@@ -21497,6 +22629,57 @@ export const MODELS = {
contextWindow: 256000,
maxTokens: 32768,
} satisfies Model<"anthropic-messages">,
+ "quiverai/arrow-2": {
+ id: "quiverai/arrow-2",
+ name: "Arrow 2",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 4,
+ output: 20,
+ cacheRead: 0.39999999999999997,
+ cacheWrite: 5,
+ },
+ contextWindow: 131072,
+ maxTokens: 131072,
+ } satisfies Model<"anthropic-messages">,
+ "quiverai/arrow-2-telos": {
+ id: "quiverai/arrow-2-telos",
+ name: "Arrow 2 Telos",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 6,
+ output: 30,
+ cacheRead: 0.6,
+ cacheWrite: 7.5,
+ },
+ contextWindow: 131072,
+ maxTokens: 131072,
+ } satisfies Model<"anthropic-messages">,
+ "sakana/fugu-max": {
+ id: "sakana/fugu-max",
+ name: "Fugu Max",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 2,
+ output: 6,
+ cacheRead: 0.25,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 1000000,
+ } satisfies Model<"anthropic-messages">,
"sakana/fugu-ultra": {
id: "sakana/fugu-ultra",
name: "Fugu Ultra",
@@ -21514,6 +22697,23 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 1000000,
} satisfies Model<"anthropic-messages">,
+ "sakana/fugu-ultra-v2": {
+ id: "sakana/fugu-ultra-v2",
+ name: "Fugu Ultra v2",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 5,
+ output: 30,
+ cacheRead: 0.5,
+ cacheWrite: 0,
+ },
+ contextWindow: 1000000,
+ maxTokens: 1000000,
+ } satisfies Model<"anthropic-messages">,
"sakana/namazu": {
id: "sakana/namazu",
name: "Sakana Namazu",
@@ -21718,6 +22918,23 @@ export const MODELS = {
contextWindow: 500000,
maxTokens: 500000,
} satisfies Model<"anthropic-messages">,
+ "spacexai/grok-4.7": {
+ id: "spacexai/grok-4.7",
+ name: "Grok 4.7",
+ api: "anthropic-messages",
+ provider: "vercel-ai-gateway",
+ baseUrl: "https://ai-gateway.vercel.sh",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 1.2,
+ output: 3.5999999999999996,
+ cacheRead: 0.3,
+ cacheWrite: 0,
+ },
+ contextWindow: 500000,
+ maxTokens: 500000,
+ } satisfies Model<"anthropic-messages">,
"spacexai/grok-build-0.1": {
id: "spacexai/grok-build-0.1",
name: "Grok Build 0.1",
@@ -21871,23 +23088,6 @@ export const MODELS = {
contextWindow: 1050000,
maxTokens: 131000,
} satisfies Model<"anthropic-messages">,
- "xiaomi/mimo-v2.5-pro-ultraspeed": {
- id: "xiaomi/mimo-v2.5-pro-ultraspeed",
- name: "MiMo V2.5 Pro UltraSpeed",
- api: "anthropic-messages",
- provider: "vercel-ai-gateway",
- baseUrl: "https://ai-gateway.vercel.sh",
- reasoning: true,
- input: ["text"],
- cost: {
- input: 1.305,
- output: 2.61,
- cacheRead: 0.0108,
- cacheWrite: 0,
- },
- contextWindow: 1048576,
- maxTokens: 131072,
- } satisfies Model<"anthropic-messages">,
"zai/glm-4.5": {
id: "zai/glm-4.5",
name: "GLM 4.5",
@@ -22101,9 +23301,9 @@ export const MODELS = {
reasoning: true,
input: ["text"],
cost: {
- input: 0.7,
- output: 2.2,
- cacheRead: 0.13,
+ input: 1.4,
+ output: 4.4,
+ cacheRead: 0.14,
cacheWrite: 0,
},
contextWindow: 1000000,
@@ -22143,22 +23343,22 @@ export const MODELS = {
contextWindow: 1000000,
maxTokens: 131000,
} satisfies Model<"anthropic-messages">,
- "zai/glm-5.3-promo-50": {
- id: "zai/glm-5.3-promo-50",
- name: "GLM 5.3 (50% off)",
+ "zai/glm-5.3-flashx": {
+ id: "zai/glm-5.3-flashx",
+ name: "GLM 5.3 FlashX",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
- input: ["text"],
+ input: ["text", "image"],
cost: {
- input: 0.7,
- output: 2.2,
- cacheRead: 0.13,
+ input: 0.37,
+ output: 1.25,
+ cacheRead: 0.075,
cacheWrite: 0,
},
- contextWindow: 1048576,
- maxTokens: 1048576,
+ contextWindow: 1000000,
+ maxTokens: 131072,
} satisfies Model<"anthropic-messages">,
"zai/glm-5v-turbo": {
id: "zai/glm-5v-turbo",
@@ -22264,6 +23464,23 @@ export const MODELS = {
contextWindow: 500000,
maxTokens: 500000,
} satisfies Model<"openai-completions">,
+ "grok-4.7": {
+ id: "grok-4.7",
+ name: "Grok 4.7",
+ api: "openai-completions",
+ provider: "xai",
+ baseUrl: "https://api.x.ai/v1",
+ reasoning: true,
+ input: ["text", "image"],
+ cost: {
+ input: 2,
+ output: 6,
+ cacheRead: 0.5,
+ cacheWrite: 0,
+ },
+ contextWindow: 500000,
+ maxTokens: 500000,
+ } satisfies Model<"openai-completions">,
"grok-build-0.1": {
id: "grok-build-0.1",
name: "Grok Build 0.1",
diff --git a/packages/ai/src/utils/oauth/xai.ts b/packages/ai/src/utils/oauth/xai.ts
index 9cb4a46575..bdfa6c9d9e 100644
--- a/packages/ai/src/utils/oauth/xai.ts
+++ b/packages/ai/src/utils/oauth/xai.ts
@@ -194,6 +194,7 @@ export function getXaiSubscriptionModel(model: Model<Api>): Model<"openai-respon
thinkingLevelMap = { off: null, minimal: null };
break;
case "grok-4.6":
+ case "grok-4.7":
thinkingLevelMap = { off: null, minimal: null, xhigh: "xhigh" };
break;
default:
diff --git a/packages/ai/test/xai-responses.test.ts b/packages/ai/test/xai-responses.test.ts
index d8d137963b..10311aaa4c 100644
--- a/packages/ai/test/xai-responses.test.ts
+++ b/packages/ai/test/xai-responses.test.ts
@@ -92,6 +92,7 @@ describe("xAI subscription Responses", () => {
["grok-4.3", "low", "low"],
["grok-4.5", "xhigh", "high"],
["grok-4.6", "xhigh", "xhigh"],
+ ["grok-4.7", "xhigh", "xhigh"],
["grok-4.20-0309-reasoning", "high", undefined],
["grok-4.20-0309-non-reasoning", "high", undefined],
["grok-build-0.1", "high", undefined],
@@ -118,6 +119,12 @@ describe("xAI subscription Responses", () => {
"high",
"xhigh",
]);
+ expect(getSupportedThinkingLevels(getXaiSubscriptionModel(getModel("xai", "grok-4.7"))!)).toEqual([
+ "low",
+ "medium",
+ "high",
+ "xhigh",
+ ]);
expect(getSupportedThinkingLevels(getXaiSubscriptionModel(getModel("xai", "grok-build-0.1"))!)).toEqual([]);
});
diff --git a/packages/coding-agent/test/model-registry.test.ts b/packages/coding-agent/test/model-registry.test.ts
index ebc09652ca..126a601d61 100644
--- a/packages/coding-agent/test/model-registry.test.ts
+++ b/packages/coding-agent/test/model-registry.test.ts
@@ -440,7 +440,7 @@ describe("ModelRegistry", () => {
describe("modelOverrides (per-model customization)", () => {
const sonnetId = "anthropic/claude-sonnet-4";
- const opusId = "anthropic/claude-opus-4";
+ const opusId = "anthropic/claude-opus-4.5";
function withOverrides(modelOverrides: Record<string, unknown>, providerFields: Record<string, unknown> = {}) {
writeRawModelsJson({ openrouter: { ...providerFields, modelOverrides } });